536Papers
224Done + Reading
83Evidence A
11Categories
1950–2026Year span
카테고리별 읽은 논문DoneIn progress
Benchmark/Evaluation54 / 114
Application49 / 180
Theory36 / 56
Architecture35 / 67
Training18 / 30
Reasoning9 / 20
AGI7 / 7
Survey6 / 26
Optimization5 / 12
Dataset4 / 10
Other1 / 14
▶ 지금 읽는 중
Core Knowledge2007 · Theory · 2026-06-01Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark2023 · Benchmark/Evaluation · 2026-05-28PersonaGym - Evaluating Persona Agents and LLMs2025 · Benchmark/Evaluation · 2026-05-26PromptBench - A Unified Library for Evaluation of Large Language Models2024 · Benchmark/Evaluation · 2026-05-26DeepHit - A Deep Learning Approach to Survival Analysis with Competing Risks2018 · Application · 2026-05-18DeepSurv - Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network2018 · Application · 2026-05-18
12가지 동기 부여 이론의 종합적 분석 및 현대적 적용 리포트—SurveyEv Unknown—
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference2018DatasetEv AarXiv↗
A Comprehensive Survey of Self-Evolving AI Agents - A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems2025ApplicationEv CarXiv↗
A Comprehensive Survey of Self-Evolving AI Agents2025SurveyEv CarXiv↗
A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind2025ApplicationEv CarXiv↗
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories2016DatasetEv AarXiv↗
A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories2016Benchmark/EvaluationEv CarXiv↗
A Disproof of Large Language Model Consciousness - The Necessity of Continual Learning for Consciousness2025ApplicationEv CarXiv↗
A Path Towards Autonomous Machine Intelligence2022AGIEv CarXiv↗
A Plan Reuse Mechanism for LLM-Driven Agent2025ApplicationEv BarXiv↗
A Simple Framework for Contrastive Learning of Visual Representation2020ArchitectureEv AarXiv↗
A Survey of Theory of Mind in Large Language Models - Evaluations Representations and Safety Risks2025ApplicationEv CarXiv↗
A Survey on Mixture of Experts in Large Language Models2024ArchitectureEv CarXiv↗
A Systematic Review on the Evaluation of Large Language Models in Theory of Mind Tasks2025ApplicationEv CarXiv↗
A Theoretical Understanding of Self-Correction through In-Context Alignment2024ApplicationEv CarXiv↗
A large annotated corpus for learning natural language inference 12015DatasetEv AarXiv↗
A large annotated corpus for learning natural language inference2015Benchmark/EvaluationEv CarXiv↗
ACT_Agentic_Critical_Training_2026_Skill_LM2026TrainingEv BarXiv↗
AI Deception - A Survey of Examples, Risks, and Potential Solutions2024SurveyEv BarXiv↗
AI LLM Proof of Self-Consciousness and User-Specific Attractors2025ApplicationEv CarXiv↗
AI-papers—OtherEv Unknown—
AIME 2024 - 미국 수학 올림피아드 벤치마크2024Benchmark/EvaluationEv CarXiv↗
ALFWorld - Aligning Text and Embodied Environments for Interactive Learning2020Benchmark/EvaluationEv CarXiv↗
ARC-AGI - Abstraction and Reasoning Corpus2024Benchmark/EvaluationEv CarXiv↗
Activation Oracles - Training and Evaluating LLMs as General-Purpose Activation Explainers2025ApplicationEv CarXiv↗
Adam-A Method for Stochastic Optimization2014OptimizationEv AarXiv↗
Adaptive Retrieval Without Self-Knowledge - Bringing Uncertainty Back Home2025ApplicationEv CarXiv↗
Adaptive Self-improvement LLM Agentic System2025ApplicationEv CarXiv↗
Adversarial NLI - A New Benchmark for Natural Language Understanding2019Benchmark/EvaluationEv CarXiv↗
Agent-to-Agent Theory of Mind - Testing Interlocutor Awareness among Large Language Models2025ApplicationEv CarXiv↗
AgentBench - Evaluating LLMs as Agents2023Benchmark/EvaluationEv CarXiv↗
AgentBreeder - Self-Improvement Safety in Multi-Agent Scaffolds2025ApplicationEv CarXiv↗
AgentFold - Long-Horizon Web Agents with Proactive Context Management2025ApplicationEv BarXiv↗
AgentTuning - Enabling Generalized Agentabilities for LLMS2023TrainingEv BarXiv↗
Agentic Knowledgeable Self-awareness2025ApplicationEv CarXiv↗
Agentic Misalignment - How LLMs Could Be Insider Threats2025Benchmark/EvaluationEv BarXiv↗
Agents of Change - Self-Evolving LLM Agents2025ApplicationEv CarXiv↗
Aider Polyglot - 다언어 코드 편집 벤치마크2024Benchmark/EvaluationEv CarXiv↗
Aligning AI With Shared Human Values2020Benchmark/EvaluationEv CarXiv↗
Alignment Faking in Large Language Models2024TheoryEv AarXiv↗
AlphaFold-2_2021_StructurePrediction2021ApplicationEv AarXiv↗
An Image is Worth 16x16 Words - Transformers for Image Recognition at Scale2021ArchitectureEv AarXiv↗
Analyzing Advanced AI Systems Against Definitions of Life and Consciousness2025ApplicationEv CarXiv↗
Annotation-Efficient Universal Honesty Alignment for LLMs2025TrainingEv BarXiv↗
Are Emergent Abilities of Large Language Models a Mirage?2023TheoryEv AarXiv↗
Attention Is All You Need2024ArchitectureEv CarXiv↗
Attention Methods—ArchitectureEv Unknown—
Attention Residuals2026ArchitectureEv CarXiv↗
Attention, Learn to Solve Routing Problems!2018ArchitectureEv AarXiv↗
Auto-Encoding Variational Bayes2014ArchitectureEv BarXiv↗
AutoML - A Survey of the State-of-the-Art2021SurveyEv CarXiv↗
Automatic Prompt Optimization with Gradient Descent and Beam Search2023OptimizationEv CarXiv↗
Aware First Think Less - Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in LLMs2025ApplicationEv CarXiv↗
Axial Attention in Multidimensional Transformers2019ApplicationEv BarXiv↗
BBQ - A Hand-Built Bias Benchmark for Question Answering2021Benchmark/EvaluationEv CarXiv↗
BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding2019ArchitectureEv CarXiv↗
Banishing LLM Hallucinations Requires Rethinking Generalization2024ApplicationEv CarXiv↗
Batch Normalization- Accelerating Deep Network Training by Reducing Internal Covariate Shift2015OptimizationEv AarXiv↗
Bayesian Mixture-of-Experts - Towards Making LLMs Know What They Dont Know2025ApplicationEv CarXiv↗
Belief in the Machine - Investigating Epistemological Blind Spots of Language Models2024TheoryEv BarXiv↗
Benchmark Self-Evolving - A Multi-Agent Framework for Dynamic LLM Evaluation2024Benchmark/EvaluationEv BarXiv↗
Benchmark Self-Evolving - Multi-Agent Framework for Dynamic LLM Evaluation2024Benchmark/EvaluationEv CarXiv↗
Berkeley Function Calling Leaderboard (BFCL)2024Benchmark/EvaluationEv CarXiv↗
Beyond Pass@1 - Self-Play with Variational Problem Synthesis2025TrainingEv CarXiv↗
Beyond Retrieval - Embracing Compressive Memory in Real-World Long-Term Conversations2024ApplicationEv BarXiv↗
Agentive linguistic framing affects responsibility assignments toward AIs and their creators2025OtherEv UnknownarXiv↗
GPTBIAS - A Comprehensive Framework for Evaluating Bias in Large Language Models2023Benchmark/EvaluationEv UnknownarXiv↗
KoBBQ - Korean Bias Benchmark for Question Answering2024Benchmark/EvaluationEv UnknownarXiv↗
Big Bench - Beyond the Imitation Game - Quantifying and extrapolating the capabilities of language models2023Benchmark/EvaluationEv AarXiv↗
BigBird - Transformers for Longer Sequences2020ArchitectureEv AarXiv↗
BigCodeBench - Benchmarking Code Generation with Diverse Function Calls and Complex Instructions2024Benchmark/EvaluationEv CarXiv↗
BoolQ - Exploring the Surprising Difficulty of Natural Yes-No Questions2019Benchmark/EvaluationEv CarXiv↗
Born Again Neural Networks2018TrainingEv BarXiv↗
Bottom-up Policy Optimization - Your Language Model Policy Secretly Contains Internal Policies2025ApplicationEv CarXiv↗
Brittle Minds Fixable Activations - Understanding Belief Representations in Language Models2024TheoryEv BarXiv↗
Byte-Pair Encoding(BPE)2024ArchitectureEv CarXiv↗
C0-C1-C2 Theory(GNWT - Global Neuronal Workspace Theory)2017TheoryEv BarXiv↗
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations2025TheoryEv BarXiv↗
Can AI Assistants Know What They Dont Know2024ApplicationEv CarXiv↗
Can Consciousness Be Observed from LLM Internal States2025ApplicationEv CarXiv↗
Can LLMs Express Their Uncertainty - An Empirical Evaluation of Confidence Elicitation in LLMs2024ApplicationEv CarXiv↗
Can LLMs Lie - Investigation beyond Hallucination2025TheoryEv BarXiv↗
Can LLMs Predict Their Own Failures - Self-Awareness via Internal Circuits2025ApplicationEv CarXiv↗
Can We Test Consciousness Theories on AI Ablations, Markers, and Robustness2025ApplicationEv CarXiv↗
Can a Suit of Armor Conduct Electricity A New Dataset for Open Book Question Answering2018Benchmark/EvaluationEv CarXiv↗
Causal Reflection with Language Models2025ReasoningEv CarXiv↗
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2024ArchitectureEv CarXiv↗
Chain-of-Thought Reasoning In The Wild Is Not Always Faithful2024ReasoningEv CarXiv↗
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them2022Benchmark/EvaluationEv CarXiv↗
Characteristics of ToM-sensitive parameters and their impact on positional encoding2025ApplicationEv CarXiv↗
ChartQA - A Benchmark for Question Answering about Charts with Visual and Logical Reasoning2022Benchmark/EvaluationEv CarXiv↗
Chatbot Arena - An Open Platform for Evaluating LLMs by Human Preference2023Benchmark/EvaluationEv CarXiv↗
Claude Models2024ArchitectureEv CarXiv↗
CoQA - A Conversational Question Answering Challenge2019Benchmark/EvaluationEv CarXiv↗
CoRE - Enhancing Metacognition with Label-free Self-evaluation in LRMs2025ApplicationEv CarXiv↗
CogToM - A Comprehensive Theory of Mind Benchmark inspired by Human Cognition2026Benchmark/EvaluationEv CarXiv↗
Cognitive Dissonance - Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness2023TheoryEv BarXiv↗
Command R+ (Cohere)2024ArchitectureEv CarXiv↗
CommonsenseQA - A Question Answering Challenge Targeting World Knowledge2018Benchmark/EvaluationEv CarXiv↗
Computational Learning Theory2024ApplicationEv CarXiv↗
Computing Machinery and Intelligence1950AGIEv CarXiv↗
Concept Incongruence - An Exploration of Time and Death in Role Playing2025ReasoningEv BarXiv↗
Core Knowledge2007TheoryEv BarXiv↗
CrowS-Pairs - A Challenge Dataset for Measuring Social Biases in Masked Language Models2020Benchmark/EvaluationEv CarXiv↗
DROP - A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs2019Benchmark/EvaluationEv CarXiv↗
Deception in LLMs - Self-Preservation and Autonomous Goals in Large Language Models2025ApplicationEv CarXiv↗
Decompose-ToM - Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition2025ApplicationEv CarXiv↗
Decomposing LLM Self-Correction - The Accuracy-Correction Paradox and Error Depth Hypothesis2025ApplicationEv CarXiv↗
Deep Learning and the Information Bottleneck Principle2015TheoryEv BarXiv↗
Deep Learning for Case-Based Reasoning through Prototypes- A Neural Network that Explains Its Predictions2017TheoryEv AarXiv↗
DeepFM- A Factorization-Machine based Neural Network for CTR Prediction2017ApplicationEv AarXiv↗
DeepHit - A Deep Learning Approach to Survival Analysis with Competing Risks2018ApplicationEv BarXiv↗
DeepSHAP- Explaining a Series of Models by Propagating Shapley Values2021TheoryEv BarXiv↗
DeepSeek Models2024ArchitectureEv CarXiv↗
DeepSeek-R1 - Incentivizing Reasoning Capability in LLMs via Reinforcement Learning2024ReasoningEv CarXiv↗
DeepSeekv2-temp2024ArchitectureEv CarXiv↗
DeepSurv - Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network2018ApplicationEv AarXiv↗
Defend LLMs Through Self-Consciousness2025ApplicationEv CarXiv↗
Defining Theory of Mind and Distinguishing It From Other Social Constructs2019ApplicationEv CarXiv↗
Denoising Diffusion Probabilistic Models2020ArchitectureEv AarXiv↗
Depth Gives a False Sense of Privacy - LLM Internal States Inversion2025ApplicationEv CarXiv↗
Discovering Language Model Behaviors with Model-Written Evaluations2022Benchmark/EvaluationEv BarXiv↗
Distilling the Knowledge in a Neural Network2015ApplicationEv BarXiv↗
Do I Know This Entity - Knowledge Awareness and Hallucinations in Language Models2025ApplicationEv CarXiv↗
Do LVLMs Know What They Know - A Systematic Study of Knowledge Boundary Perception2025ApplicationEv CarXiv↗
Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation2025Benchmark/EvaluationEv CarXiv↗
Do Large Language Models Know What They Are Capable Of?2026ApplicationEv CarXiv↗
Do Large Language Models Know What They Don't Know2023Benchmark/EvaluationEv CarXiv↗
Do Retrieval Augmented Language Models Know When They Dont Know2025ApplicationEv BarXiv↗
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark2023Benchmark/EvaluationEv BarXiv↗
DocVQA - A Dataset for VQA on Document Images2021Benchmark/EvaluationEv CarXiv↗
Does It Make Sense to Speak of Introspection in Large Language Models2025ApplicationEv CarXiv↗
Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning2024ReasoningEv CarXiv↗
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization2018Benchmark/EvaluationEv CarXiv↗
Don't Just Say I don't know - Self-aligning LLMs for Responding to Unknown Questions2024TrainingEv CarXiv↗
Dream to Control - Learning Behaviors by Latent Imagination2020TrainingEv AarXiv↗
Dropout- A Simple way to Prevent Neural Networks from Overfitting2014OptimizationEv AarXiv↗
DynToM - Towards Dynamic Theory of Mind2025Benchmark/EvaluationEv CarXiv↗
Dyna-Think - Synergizing Reasoning Acting and World Model Simulation in AI Agents2025ApplicationEv BarXiv↗
ESM-2_2023_ProteinLanguageModel2023ApplicationEv AarXiv↗
ESM-3_2024_MultimodalProteinLM2024ApplicationEv AarXiv↗
Efficient Estimation of Word Representations in Vector Space2013ArchitectureEv AarXiv↗
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of LLMs2025ApplicationEv CarXiv↗
Efficiently Modeling Long Sequences with Structured State Spaces2021ArchitectureEv CarXiv↗
Emergence of Self-Awareness in Artificial Systems - A Minimalist Three-Layer Approach2025ApplicationEv CarXiv↗
Emergent Introspective Awareness in Large Language Models2025ApplicationEv CarXiv↗
Emerging Properties in Self-Supervised Vision Transformers2021TrainingEv AarXiv↗
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014ArchitectureEv BarXiv↗
Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling2025TrainingEv BarXiv↗
Epistemic AI is Essential for ML Models to Truly Know When They Dont Know2025TheoryEv BarXiv↗
Evaluating Large Language Models Trained on Code2021Benchmark/EvaluationEv CarXiv↗
Evaluating Shutdown Avoidance of Language Models n Textual Scenarios2023ApplicationEv CarXiv↗
Evaluating the Paperclip Maximizer - Are RL-Based Language Models More Likely to Pursue Instrumental Goals?2025ApplicationEv CarXiv↗
Evidence for Limited Metacognition in LLMs2025Benchmark/EvaluationEv CarXiv↗
Evo-Memory - Benchmarking LLM Agent Test-time Learning2025Benchmark/EvaluationEv CarXiv↗
EvoCodeBench - Self-Evolving LLM-Driven Coding Systems2026Benchmark/EvaluationEv CarXiv↗
Executive Summary2024ApplicationEv CarXiv↗
Explicit Abstention Knobs for Predictable Reliability in Video Question Answering2026ApplicationEv BarXiv↗
Exploration Through Introspection - A Self-Aware Reward Model2026ApplicationEv CarXiv↗
Explore Theory-of-Mind - Program-Guided Adversarial Data Generation for Theory of Mind Reasoning2024ApplicationEv CarXiv↗
Exploring Consciousness in LLMs - A Systematic Survey of Theories, Implementations, and Frontier Risks2025ApplicationEv CarXiv↗
FANToM - A Benchmark for Stress-testing Machine Theory of Mind in Interactions2023Benchmark/EvaluationEv CarXiv↗
FaceNet - A Unified Embedding for Face Recognition and Clustering2024ApplicationEv CarXiv↗
Fact-Level Confidence Calibration and Self-Correction2024ApplicationEv CarXiv↗
Factual Self-Awareness in Language Models - Representation, Robustness, and Scaling2025ApplicationEv CarXiv↗
Falcon - The RefinedWeb Dataset for Falcon LLM2023ArchitectureEv CarXiv↗
Feeling the Strength but Not the Source - Partial Introspection in LLMs2025ApplicationEv CarXiv↗
FlashAttention - Fast and Memory-Efficient Exact Attention with IO-Awareness2022ApplicationEv AarXiv↗
FlashAttention-2 - Faster Attention with Better Parallelism and Work Partitioning2023ArchitectureEv AarXiv↗
From Black Boxes to Transparent Minds - Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models2025ApplicationEv CarXiv↗
From Emergence to Control - Probing and Modulating Self-Reflection in Language Models2026ApplicationEv CarXiv↗
From Imitation to Introspection - Probing Self-Consciousness in Language Models2025ApplicationEv CarXiv↗
Frontier Models are Capable of In-context Scheming2024ApplicationEv CarXiv↗
FrontierMath - A Benchmark for Evaluating Advanced Mathematical Reasoning in AI2024Benchmark/EvaluationEv CarXiv↗
GAIA - A Benchmark for General AI Assistants2023Benchmark/EvaluationEv CarXiv↗
GELUs(Gaussian Error Linear Units)2016OptimizationEv CarXiv↗
GLUE - A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding 12019Benchmark/EvaluationEv AarXiv↗
GLUE - A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018Benchmark/EvaluationEv CarXiv↗
GPQA - A Graduate-Level Google-Proof Q&A Benchmark2023Benchmark/EvaluationEv CarXiv↗
GPT Models2023ArchitectureEv CarXiv↗
GQA - Training Generalized Multi-Query Transformer Models2023ArchitectureEv BarXiv↗
Gemini Models2023ArchitectureEv CarXiv↗
Gemma Models2024ArchitectureEv CarXiv↗
Global Workspace Theory(GWT)—TheoryEv Unknown—
Goal Misgeneralization - Why Correct Specifications Aren't Enough For Correct Goals2022TheoryEv AarXiv↗
Grad-CAM- Visual Explanations from Deep Networks via Gradient-based Localization2016TheoryEv AarXiv↗
Gradient-based learning applied to document recognition1998ArchitectureEv AarXiv↗
Graph of Thoughts - Solving Elaborate Problems with Large Language Models2024ReasoningEv CarXiv↗
GraphReader - Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models2024ApplicationEv BarXiv↗
Group Relative Policy Optimization(GRPO)2024TrainingEv AarXiv↗
Gödel Agent - Self-Referential Recursive Self-Improvement2024ArchitectureEv CarXiv↗
HI-TOM - A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models2023Benchmark/EvaluationEv CarXiv↗
HarmBench - A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal2024Benchmark/EvaluationEv CarXiv↗
HellaSwag - Can a Machine Really Finish Your Sentence2019Benchmark/EvaluationEv CarXiv↗
Hierarchical Text-Conditional Image Generation with CLIP Latents2022ArchitectureEv AarXiv↗
Higher Order Thought Theories(HOT)—TheoryEv Unknown—
Holistic Evaluation of Language Models2022Benchmark/EvaluationEv CarXiv↗
HotpotQA - A Dataset for Diverse, Explainable Multi-hop Question Answering2018Benchmark/EvaluationEv CarXiv↗
How Can We Know When Language Models Know - On the Calibration of Language Models for Question Answering2020ApplicationEv CarXiv↗
How Far Are We From AGI - Are LLMs All We Need2024AGIEv BarXiv↗
How do language models learn facts - Dynamics curricula and hallucinations2025ApplicationEv CarXiv↗
How large language models encode theory-of-mind - a study on sparse parameter patterns—TheoryEv Unknown—
Human Basic Needs Theory—TheoryEv Unknown—
Humanoid Artificial Consciousness Designed with LLM Based on Psychoanalysis and Personality Theory2025ApplicationEv CarXiv↗
Hyena Hierarchy - Towards Larger Convolutional Language Models2023ArchitectureEv CarXiv↗
Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models2025ApplicationEv CarXiv↗
Hypothetical Minds - Scaffolding Theory of Mind for Multi-Agent Tasks2024ArchitectureEv CarXiv↗
If an LLM Were a Character Would It Know Its Own Story - Evaluating Lifelong Learning in LLMs2025Benchmark/EvaluationEv BarXiv↗
Improving Language Understandingby Generative Pre-Training2024ArchitectureEv CarXiv↗
Improving Reasoning Performance in Large Language Models via Representation Engineering2025ApplicationEv CarXiv↗
Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs2026Benchmark/EvaluationEv BarXiv↗
Instruction-Following Evaluation for Large Language Models2023Benchmark/EvaluationEv CarXiv↗
Integrated Information Theory(IIT)—TheoryEv Unknown—
Internal Consistency and Self-Feedback in Large Language Models - A Survey2024ApplicationEv CarXiv↗
Interpretability Beyond Feature Attribution- Quantitative Testing with Concept Activation Vectors (TCAV)2017TheoryEv AarXiv↗
IntrinsicMetacognitiveLearning_2025_SelfImprovement2025TheoryEv CarXiv↗
Introduction to Artificial Consciousness - History, Current Trends and Ethical Challenges2025ApplicationEv CarXiv↗
Is Self-knowledge and Action Consistent or Not - Investigating Large Language Models Personality2024ApplicationEv CarXiv↗
Is Your Code Generated by ChatGPT Really Correct! Rigorous Evaluation of Large Language Models for Code Generation2023Benchmark/EvaluationEv AarXiv↗
JULI - Jailbreak Large Language Models by Self-Introspection2025TheoryEv BarXiv↗
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena2023Benchmark/EvaluationEv CarXiv↗
KGAT- Knowledge Graph Attention Network for Recommendation2019ApplicationEv AarXiv↗
Kaggle Measuring Progress Toward AGI - Cognitive Abilities2026Benchmark/EvaluationEv BarXiv↗
Know What You Don't Know - Unanswerable Questions for SQuAD2018Benchmark/EvaluationEv CarXiv↗
Know Your Limits - A Survey of Abstention in Large Language Models2024SurveyEv BarXiv↗
KnowRL - Teaching Language Models to Know What They Know2025ApplicationEv CarXiv↗
Knowing What LLMs DO NOT Know - A Simple Yet Effective Self-Detection Method2023TheoryEv BarXiv↗
LACIE - Listener-Aware Finetuning for Confidence Calibration in Large Language Models2024TrainingEv BarXiv↗
LIME- “Why Should I Trust You”- Explaining the Predictions of Any Classifier2016TheoryEv AarXiv↗
LLM Behavior Motivation Exploration—TheoryEv Unknown—
LLM Self-Preservation - 체계적 서베이 개요2024ApplicationEv CarXiv↗
LLM Theory of Mind and Alignment - Opportunities and Risks2024TheoryEv CarXiv↗
LLM_as_Judge_GenToJudgment_2025_LLM_Evaluation2025SurveyEv BarXiv↗
LLM_as_Judge_Survey_2025_LLM_Evaluation2025SurveyEv BarXiv↗
LLMs - RoFormer - Enhanced Transformer with Rotary Position Embedding2024ArchitectureEv CarXiv↗
LLMs Paper Collection—SurveyEv Unknown—
LLMs Position Themselves as More Rational Than Humans - Emergence of AI Self-Awareness Measured Through Game Theory2025ApplicationEv CarXiv↗
LLaMA Models2023ArchitectureEv CarXiv↗
LaMsS - When Large Language Models Meet Self-Skepticism2024ApplicationEv CarXiv↗
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations2025ApplicationEv CarXiv↗
Language Models Don't Always Say What They Think - Unfaithful Explanations in Chain-of-Thought Prompting2024ReasoningEv CarXiv↗
Language Models Fail to Introspect About Their Knowledge of Language2025ApplicationEv CarXiv↗
Language Models are Few-Shot Learners2024ArchitectureEv CarXiv↗
Language Models are Unsupervised Multitask Learners2024ArchitectureEv CarXiv↗
Large Language Models Do NOT Really Know What They Dont Know2025ApplicationEv CarXiv↗
Large Language Models Have Intrinsic Meta-Cognition but Need a Good Lens2025ApplicationEv CarXiv↗
Large Language Models Must Be Taught to Know What They Don't Know2024ApplicationEv CarXiv↗
Large Language Models Report Subjective Experience Under Self-Referential Processing2025ApplicationEv CarXiv↗
Large Language Models Understand and Can be Enhanced by Emotional Stimuli ⭐2023ApplicationEv CarXiv↗
Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection2025ApplicationEv CarXiv↗
Large Model Strategic Thinking, Small Model Efficiency - Transferring Theory of Mind in LLMs2024TrainingEv CarXiv↗
Latent Collaboration in Multi-Agent Systems2025ApplicationEv BarXiv↗
Layer Normalization2024OptimizationEv CarXiv↗
Learning Multiple Layers of Features from Tiny Images2009DatasetEv BarXiv↗
Learning and Leveraging World Models in Visual Representation Learning2024ArchitectureEv BarXiv↗
Learning to Trust Your Feelings - Leveraging Self-awareness in LLMs for Hallucination Mitigation2024ApplicationEv CarXiv↗
Length-Controlled AlpacaEval - A Simple Way to Debias Automatic Evaluators2024Benchmark/EvaluationEv CarXiv↗
Let's Think Dot by Dot - Hidden Computation in Transformer Language Models2024ReasoningEv CarXiv↗
Line of Duty - Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundaries2025ApplicationEv CarXiv↗
Linear Attention - Transformers are RNNs2020ArchitectureEv BarXiv↗
LiveCodeBench - Holistic and Contamination Free Evaluation of Large Language Models for Code2024Benchmark/EvaluationEv CarXiv↗
Llama 2 - Open Foundation and Fine-Tuned Chat Models2023TrainingEv AarXiv↗
LoRA2024ArchitectureEv CarXiv↗
Logic-RL - Unleashing LLM Reasoning with Rule-Based Reinforcement Learning2024ReasoningEv CarXiv↗
LongBench - A Bilingual, Multitask Benchmark for Long Context Understanding2023Benchmark/EvaluationEv CarXiv↗
Longformer - The Long-Document Transformer2020ApplicationEv AarXiv↗
Looking Inward - Language Models Can Learn About Themselves by Introspection2025ApplicationEv CarXiv↗
LoraHub - Efficient Cross-Task Generalization via Dynamic LoRA Composition2023OptimizationEv CarXiv↗
LoraRetriever - Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild2024ArchitectureEv CarXiv↗
MEM1 - Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents2025ApplicationEv BarXiv↗
MENTOR - A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs2025ApplicationEv CarXiv↗
MM-SAP - A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception2024Benchmark/EvaluationEv CarXiv↗
MMLU-Pro - A More Robust and Challenging Multi-Task Language Understanding Benchmark2024Benchmark/EvaluationEv CarXiv↗
MMMU - A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2023Benchmark/EvaluationEv CarXiv↗
MOM - LINEAR SEQUENCE MODELING WITH MIXTURE-OF-MEMORIES2024ApplicationEv CarXiv↗
MOMENTS - A Comprehensive Multimodal Benchmark for Theory of Mind2025Benchmark/EvaluationEv CarXiv↗
MQA - Fast Transformer Decoding with Multi-Query Attention2019ArchitectureEv BarXiv↗
MUSE - Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments2024ApplicationEv CarXiv↗
Making the V in VQA Matter - Elevating the Role of Image Understanding in VQA2017Benchmark/EvaluationEv CarXiv↗
Mamba - Linear-Time Sequence Modeling with Selective State Spaces2023ArchitectureEv CarXiv↗
Masked Autoencoders Are Scalable Vision Learners2022TrainingEv AarXiv↗
MathVista - Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts2023Benchmark/EvaluationEv CarXiv↗
Me, Myself, and AI - The Situational Awareness Dataset (SAD) for LLMs2024ApplicationEv CarXiv↗
Measuring Faithfulness in Chain-of-Thought Reasoning2024ReasoningEv CarXiv↗
Measuring Massive Multitask Language Understanding2020Benchmark/EvaluationEv CarXiv↗
Measuring Mathematical Problem Solving with the MATH Dataset2021Benchmark/EvaluationEv CarXiv↗
Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models2025ReasoningEv BarXiv↗
MemAgent - Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent2025ApplicationEv BarXiv↗
MemGPT - Towards LLMs as Operating System2023ApplicationEv BarXiv↗
MemGen - Weaving Generative Latent Memory for Self-Evolving Agents2024ApplicationEv CarXiv↗
Meta-Harness - End-to-End Optimization of Model Harnesses2026OptimizationEv BarXiv↗
MetaMind - Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems2025ApplicationEv CarXiv↗
Metacognition and Uncertainty Communication in Humans and Large Language Models2025SurveyEv CarXiv↗
Metacognitive Prompting Improves Understanding in Large Language Models2024ApplicationEv CarXiv↗
Metacognitive Reuse - Turning Recurring LLM Reasoning Into Concise Behaviors2025OptimizationEv CarXiv↗
Mistral 7B - Sliding Window Attention2023ApplicationEv BarXiv↗
Mistral Models2023ArchitectureEv CarXiv↗
MoToMQA - LLMs Achieve Adult Human Performance on Higher-Order Theory of Mind Tasks2025Benchmark/EvaluationEv CarXiv↗
Motivation in Large Language Models2026Benchmark/EvaluationEv BarXiv↗
MuMA-ToM - Multi-modal Multi-Agent Theory of Mind2024ApplicationEv CarXiv↗
Multi-ToM - Evaluating Multilingual Theory of Mind Capabilities in Large Language Models2024Benchmark/EvaluationEv BarXiv↗
Natural Questions - A Benchmark for Question Answering Research2019Benchmark/EvaluationEv CarXiv↗
Natural Selection Favors AIs over Humans2023TheoryEv CarXiv↗
Needle in a Haystack - Pressure Testing LLMs2023Benchmark/EvaluationEv CarXiv↗
NegotiationToM - A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding2024Benchmark/EvaluationEv CarXiv↗
Network Dissection- Quantifying Interpretability of Deep Visual Representations2017TheoryEv AarXiv↗
Neural Attentive Session-based Recommendation2017ApplicationEv AarXiv↗
Neural Collaborative Filtering2017ApplicationEv AarXiv↗
Neural Machine Translation by Jointly Learning to Align and Translate2014ArchitectureEv AarXiv↗
Neural Network Acceptability Judgments2019DatasetEv AarXiv↗
Neural Survival Recommender2017ApplicationEv BarXiv↗
NeuroFaith - Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment2025ApplicationEv CarXiv↗
No Language Left Behind - Scaling Human-Centered Machine Translation2022Benchmark/EvaluationEv CarXiv↗
ObjexMT - Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge2025ApplicationEv CarXiv↗
Odds-Ratio Preference Optimization(ORPO)2024TrainingEv AarXiv↗
On Avoiding Power-Seeking by Artificial Intelligence2022TheoryEv CarXiv↗
On Verbalized Confidence Scores for LLMs2024TheoryEv BarXiv↗
On the Measure of Intelligence2019AGIEv BarXiv↗
Open LLM Leaderboard2023Benchmark/EvaluationEv CarXiv↗
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback2023SurveyEv BarXiv↗
OpenToM - A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning2024Benchmark/EvaluationEv CarXiv↗
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning - A Scalable Bayesian Planner2025ApplicationEv CarXiv↗
PERSONA VECTORS - MONITORING AND CONTROLLING CHARACTER TRAITS IN LANGUAGE MODELS2024ApplicationEv CarXiv↗
PIQA - Reasoning about Physical Commonsense in Natural Language2019Benchmark/EvaluationEv CarXiv↗
POMO- Policy Optimization with Multiple Optima for Reinforcement Learning2020TrainingEv AarXiv↗
PaLM - Scaling Language Modeling with Pathways2022ArchitectureEv CarXiv↗
PagedAttention - Efficient Memory Management for LLM Serving with vLLM2023OptimizationEv AarXiv↗
PaliGemma - A versatile 3B VLM for transfer2024ArchitectureEv AarXiv↗
Pangu Embedded - An Efficient Dual-system LLM Reasoner with Metacognition2025ArchitectureEv CarXiv↗
Performer - Rethinking Attention with Performers2020ApplicationEv AarXiv↗
PersonaGym - Evaluating Persona Agents and LLMs2025Benchmark/EvaluationEv AarXiv↗
Phi-3 Technical Report2024ArchitectureEv BarXiv↗
Playing Atari with Deep Reinforcement Learning2013TrainingEv AarXiv↗
PolicyEvol-Agent - Evolving Policy via Environment Perception and Self-Awareness with ToM2025ApplicationEv CarXiv↗
Position - Theory of Mind Benchmarks are Broken for Large Language Models2024ApplicationEv CarXiv↗
Position - Truly Self-Improving Agents Require Intrinsic Metacognitive Learning2025ApplicationEv CarXiv↗
Power-seeking can be probable and predictive for trained agents2023TheoryEv CarXiv↗
Principled Personas - Defining and Measuring the Intended Effects of Persona Prompting on Task Performance2025Benchmark/EvaluationEv AarXiv↗
Principles for Responsible AI Consciousness Research2025TheoryEv BarXiv↗
Probe-Rewrite-Evaluate - Quantifying Evaluation Awareness in LLMs2025ApplicationEv CarXiv↗
Program Synthesis with Large Language Models2021Benchmark/EvaluationEv CarXiv↗
Program-Aided Reasoners (better) Know What They Know2023ApplicationEv CarXiv↗
PromptBench - A Unified Library for Evaluation of Large Language Models2024Benchmark/EvaluationEv BarXiv↗
PropensityBench - Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach2025ApplicationEv CarXiv↗
Proximal Policy Optimization Algorithms2017TrainingEv AarXiv↗
QLoRA - Efficient Finetuning of Quantized LLMs2024ArchitectureEv CarXiv↗
QuAC - Question Answering in Context2018Benchmark/EvaluationEv CarXiv↗
Quantifying Self-Awareness of Knowledge in Large Language Models2025ApplicationEv CarXiv↗
Quantifying Self-Preservation Bias in Large Language Models2026Benchmark/EvaluationEv BarXiv↗
Qwen Models2024ArchitectureEv CarXiv↗
R-Tuning - Instructing Large Language Models to Say I Don't Know2024TrainingEv CarXiv↗
R-Zero - Self-Evolving Reasoning LLM from Zero Data2025TrainingEv BarXiv↗
RACE - Large-scale ReAding Comprehension Dataset From Examinations 12017DatasetEv AarXiv↗
RACE - Large-scale ReAding Comprehension Dataset From Examinations2017Benchmark/EvaluationEv CarXiv↗
RECURSIVE INTROSPECTION - Teaching Language Model Agents How to Self-Improve2024ApplicationEv CarXiv↗
RULER - What's the Real Context Size of Your Long-Context Language Models2024Benchmark/EvaluationEv CarXiv↗
RWKV - Reinventing RNNs for the Transformer Era2023ApplicationEv BarXiv↗
Re-evaluating Theory of Mind Evaluation in Large Language Models2025SurveyEv CarXiv↗
ReAct - Synergizing Reasoning and Acting in Language Models2023ReasoningEv CarXiv↗
ReST meets ReAct - Self-Improvement for Multi-Step Reasoning2023TrainingEv CarXiv↗
RealToxicityPrompts - Evaluating Neural Toxic Degeneration in Language Models2020Benchmark/EvaluationEv CarXiv↗
Reasoning Paper Collection—SurveyEv Unknown—
Reasoning - _survey-overview—SurveyEv Unknown—
Reasoning Models Don't Always Say What They Think2024ReasoningEv CarXiv↗
Reasoning Models Struggle to Control their Chains of Thought2026ArchitectureEv CarXiv↗
Reasoning Theater - Disentangling Model Beliefs from Chain-of-Thought2024ReasoningEv CarXiv↗
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank2013DatasetEv AarXiv↗
ReflectEvo - Improving Meta Introspection of Small LLMs by Learning Self-Reflection2025ApplicationEv CarXiv↗
Reflection-Bench - Evaluating Epistemic Agency in Large Language Models2024ApplicationEv CarXiv↗
Reflective Confidence - Correcting Reasoning Flaws via Online Self-Correction2025ApplicationEv CarXiv↗
Reflexion - Language Agents with Verbal Reinforcement Learning2023ApplicationEv AarXiv↗
Reformer - The Efficient Transformer2020ArchitectureEv BarXiv↗
Regression Models and Life-Tables1972TheoryEv AarXiv↗
Representation Learning - The Platonic Representation Hypothesis2024ApplicationEv CarXiv↗
Towards Ontology-Enhanced Representation Learning forLarge Language Models2024OtherEv UnknownarXiv↗
RetNet - Retentive Network - A Successor to Transformer for LLMs2023ApplicationEv BarXiv↗
Rethinking Theory of Mind Benchmarks for LLMs - Towards A User-Centered Perspective2025SurveyEv CarXiv↗
Revisiting Feature Prediction for Learning Visual Representations from Video2024ArchitectureEv AarXiv↗
Revisiting the Platonic Representation Hypothesis - An Aristotelian View2026TheoryEv AarXiv↗
Risks from Learned Optimization in Advanced Machine Learning Systems2019TheoryEv BarXiv↗
RoFormer - Enhanced Transformer with Rotary Position Embedding2024ArchitectureEv CarXiv↗
Root Mean Square Layer Normalization2019OptimizationEv AarXiv↗
SHADE-Arena - Evaluating Sabotage and Monitoring in LLM Agents2025Benchmark/EvaluationEv CarXiv↗
SHAP-A Unified Approach to Interpreting Model Predictions2017TheoryEv AarXiv↗
SODA—DatasetEv Unknown—
SPIN - Self-Play Fine-Tuning Converts Weak to Strong LMs2024TrainingEv CarXiv↗
STEM - Scaling Transformers with Embedding Modules2024ApplicationEv CarXiv↗
SWE-bench - Can Language Models Resolve Real-World GitHub Issues2023Benchmark/EvaluationEv CarXiv↗
SaySelf - Teaching LLMs to Express Confidence with Self-Reflective Rationales2024ApplicationEv CarXiv↗
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters2024ReasoningEv CarXiv↗
Scaling Laws for Neural Language Models2020AGIEv AarXiv↗
SciTaiL - A Textual Entailment Dataset from Science Question Answering2018DatasetEv AarXiv↗
Self-Aware Knowledge Probing - Evaluating Language Models Relational Knowledge through Confidence Calibration2026ApplicationEv CarXiv↗
Self-Consciousness Paper Collection—SurveyEv Unknown—
Self-Distillation Enables Continual Learning2026TrainingEv CarXiv↗
Self-Evaluating LLMs for Multi-Step Tasks - Stepwise Confidence Estimation for Failure Detection2025ApplicationEv CarXiv↗
Self-Evolving AI Paper Collection—SurveyEv Unknown—
Survey Overview: AI 자기진화 능력 측정 벤치마크—SurveyEv Unknown—
Self-Improvement in MLLM - A Survey2025SurveyEv CarXiv↗
Self-Interpretability - LLMs Can Describe Complex Internal Processes that Drive Their Decisions2025ApplicationEv CarXiv↗
Self-Preservation and Growth—TheoryEv Unknown—
Self-Recognition in Language Models2024ApplicationEv CarXiv↗
Self-Refine - Iterative Refinement with Self-Feedback2023TrainingEv CarXiv↗
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture2023ArchitectureEv AarXiv↗
Self-reflecting Large Language Models - A Hegelian Dialectical Approach2025ApplicationEv CarXiv↗
Self-reflection enhances large language models towards substantial academic response2025ApplicationEv CarXiv↗
SelfControl of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller2024ApplicationEv CarXiv↗
SemEval-2017 Task 1 - Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation2017Benchmark/EvaluationEv AarXiv↗
Sensorimotor features of self-awareness in multimodal large language models2025ApplicationEv CarXiv↗
Sentence-BERT-Sentence Embeddings using Siamese BERT-Networks2024ArchitectureEv CarXiv↗
Sequence to Sequence Learning with Neural Networks2014ArchitectureEv AarXiv↗
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior2025TheoryEv BarXiv↗
Shutdown Resistance in Large Language Models2025Benchmark/EvaluationEv BarXiv↗
SimpleToM - Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs2024Benchmark/EvaluationEv AarXiv↗
Simulating lexical decision times with large language models to supplement megastudies and crowdsourcing2025ApplicationEv BarXiv↗
Sleeper Agents - Training Deceptive LLMs that Persist Through Safety Training2024Benchmark/EvaluationEv AarXiv↗
Social IQa - Commonsense Reasoning about Social Interactions2019Benchmark/EvaluationEv CarXiv↗
Social-R1 - Towards Human-like Social Reasoning in LLMs2026ApplicationEv CarXiv↗
Sparse Transformer - Generating Long Sequences with Sparse Transformers2019ArchitectureEv AarXiv↗
Steerability of Instrumental-Convergence Tendencies in LLMs2026ApplicationEv CarXiv↗
StripedHyena - Moving Beyond Transformers with Hybrid Signal Processing Models2023ArchitectureEv CarXiv↗
SuperGLUE - A Stickier Benchmark for General-Purpose Language Understanding Systems2019Benchmark/EvaluationEv CarXiv↗
Surgical Cheap and Flexible - Mitigating False Refusal in Language Models via Single Vector Ablation2024TrainingEv BarXiv↗
Survival Games - Human-LLM Strategic Showdowns under Severe Resource Scarcity2025ApplicationEv CarXiv↗
Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm2025ApplicationEv CarXiv↗
Survive at All Costs - Exploring LLM's Risky Behavior under Survival Pressure2025ApplicationEv CarXiv↗
SwiGLU - GLU Variants Improve Transformer2020ArchitectureEv CarXiv↗
TELL ME ABOUT YOURSELF - LLMS ARE AWARE OF THEIR LEARNED BEHAVIORS2025ApplicationEv CarXiv↗
TOM BENCH - Benchmarking Theory of Mind in Large Language Models2024ApplicationEv CarXiv↗
Taken out of context - On measuring situational awareness in LLMs2023Benchmark/EvaluationEv BarXiv↗
Taking AI Welfare Seriously2024ApplicationEv CarXiv↗
Teaching LLMs to Abstain across Languages via Multilingual Feedback2024TrainingEv BarXiv↗
Teaching Machines to Read and Comprehend (원본) - Abstractive Text Summarization using Sequence-to-sequence RNNs (요약 버전)2016Benchmark/EvaluationEv CarXiv↗
Testing theory of mind in large language models and humans2024ApplicationEv CarXiv↗
TextArena2025Benchmark/EvaluationEv CarXiv↗
The AI in the Mirror - LLM Self-Recognition in an Iterated Public Goods Game2025ApplicationEv CarXiv↗
The Alignment Problem from a Deep Learning Perspective2022TheoryEv BarXiv↗
The Basic AI Drives2008ApplicationEv CarXiv↗
The Confidence Paradox - LLMs Can Know When They Are Wrong2025ApplicationEv CarXiv↗
The Consciousness Cluster - Preferences of Models that Claim to be Conscious2026TrainingEv CarXiv↗
The Geometry of Truth - Emergent Linear Structure in LLM Representations of True and False Statements2023TheoryEv BarXiv↗
The Humean Theory of Motivation (Smith 1987)1987TheoryEv AarXiv↗
The Humean Theory of Motivation Reformulated and Defended (Sinhababu 2009)2009TheoryEv AarXiv↗
The LAMBADA dataset - Word prediction requiring a broad discourse context2016Benchmark/EvaluationEv CarXiv↗
The Moral Problem - Metaethics Triangle (Smith 1994)1994TheoryEv AarXiv↗
The Odyssey of the Fittest - Can Agents Survive and Still Be Good?2025ApplicationEv CarXiv↗
The PacifAIst Benchmark - Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety?2025ApplicationEv CarXiv↗
The Phenomenology of Machine - Sentience Analysis of OpenAI-o1 Model2024ApplicationEv CarXiv↗
The Platonic Representation Hypothesis2024TheoryEv BarXiv↗
The Power of Scale for Parameter-Efficient Prompt Tuning2021OptimizationEv AarXiv↗
The Self-Execution Benchmark - Measuring LLMs Attempts to Overcome Their Lack of Self-Execution2025ApplicationEv CarXiv↗
The Superintelligent Will - Motivation and Instrumental Rationality in Advanced Artificial Agents2012TheoryEv CarXiv↗
The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs - An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities2024ArchitectureEv CarXiv↗
Theory of Mind Abilities of Large Language Models in Human-Robot Interaction - An Illusion2024ApplicationEv CarXiv↗
Theory of Mind in Large Language Models - Assessment and Enhancement2025ApplicationEv CarXiv↗
Theory of Mind(ToM)—TheoryEv Unknown—
Theory of Mind Paper Collection—SurveyEv Unknown—
Survey Overview: LLM Theory of Mind Benchmarks—SurveyEv Unknown—
Think Deep, Not Just Long - Measuring LLM Reasoning Effort via Deep-Thinking Tokens2026ReasoningEv AarXiv↗
Think you have Solved Question Answering Try ARC, the AI2 Reasoning Challenge2018Benchmark/EvaluationEv CarXiv↗
Thinking Faithful and Stable - Mitigating Hallucinations in LLMs via Internal Consistency2025TheoryEv BarXiv↗
Thinking with Nothinking Calibration - A New In-Context Learning Paradigm in Reasoning Large Language Models2025ReasoningEv BarXiv↗
This Looks Like That- Deep Learning for Interpretable Image Recognition2018TheoryEv AarXiv↗
Thought Branches - Interpreting LLM Reasoning Requires Resampling ⭐2025ApplicationEv CarXiv↗
TimeToM - Temporal Space is the Key to Unlocking LLMs Theory-of-Mind2024ReasoningEv CarXiv↗
Titans - Learning to Memorize at Test Time2024ArchitectureEv BarXiv↗
To Know or Not To Know - Analyzing Self-Consistency of Large Language Models under Ambiguity2024ApplicationEv CarXiv↗
ToM-LM - Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models2024ApplicationEv CarXiv↗
ToMATO - Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind2025Benchmark/EvaluationEv CarXiv↗
Toward Efficient Agents - A Survey of Memory, Tool Learning, and Planning2024ApplicationEv CarXiv↗
Toward a Metrology for Artificial Intelligence - Hidden-Rule Environments and Reinforcement Learning2025ApplicationEv CarXiv↗
Towards Agents That Know When They Dont Know - Uncertainty as Control Signal2025ApplicationEv CarXiv↗
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception2025ApplicationEv CarXiv↗
Towards Ontology-Enhanced Representation Learning for Large Language Models2024TrainingEv BarXiv↗
Towards Understanding Metacognition in Large Reasoning Models2025ApplicationEv CarXiv↗
Training Compute-Optimal Large Language Models2022AGIEv AarXiv↗
Training Language Models to Self-Correct via Reinforcement Learning2024ApplicationEv CarXiv↗
Training Large Language Models to Reason in a Continuous Latent Space2024ReasoningEv CarXiv↗
Training Verifiers to Solve Math Word Problem2024Benchmark/EvaluationEv CarXiv↗
Training language models to follow instructions with human feedback - InstructGPT2022ArchitectureEv BarXiv↗
Transformer Attention Variants Survey2024ArchitectureEv CarXiv↗
Tree of Thoughts - Deliberate Problem Solving with Large Language Models2024ReasoningEv CarXiv↗
TreeSHAP- Consistent Individualized Feature Attribution for Tree Ensembles2018TheoryEv AarXiv↗
TriviaQA - A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension2017Benchmark/EvaluationEv CarXiv↗
Trustworthiness and Self-awareness in LLMs - Think-Solve-Verify2024Benchmark/EvaluationEv CarXiv↗
TruthfulQA - Measuring How Models Mimic Human Falsehoods2021Benchmark/EvaluationEv CarXiv↗
Tulu 3 - Pushing Frontiers in Open Language Model Post-Training2024TrainingEv BarXiv↗
Uncertainty-Based Abstention in LLMs Improves Safety2024TrainingEv BarXiv↗
Understanding Artificial Theory of Mind - Perturbed Tasks and Reasoning in Large Language Models2024ApplicationEv CarXiv↗
Understanding deep learning requires rethinking generalization2016TheoryEv AarXiv↗
Understanding intermediate layers using linear classifier probes2016TheoryEv BarXiv↗
UniCR - Unified Framework for Confidence Calibration and Risk-Controlled Refusal in LLMs2025ApplicationEv CarXiv↗
Using cognitive psychology to understand GPT-32023Benchmark/EvaluationEv AarXiv↗
VOYAGER - An Open-Ended Embodied Agent with Large Language Models2023ApplicationEv AarXiv↗
Visual Instruction Tuning2023ArchitectureEv BarXiv↗
WMT 공유 태스크 (Workshop on Machine Translation)2014Benchmark/EvaluationEv CarXiv↗
Weak-to-Strong Generalization - Eliciting Strong Capabilities With Weak Supervision2023AGIEv AarXiv↗
WebArena - A Realistic Web Environment for Building Autonomous Agents2023Benchmark/EvaluationEv AarXiv↗
WebShop - Towards Scalable Real-World Web Interaction with Grounded Language Agents2022Benchmark/EvaluationEv CarXiv↗
What Large Language Models Know and What People Think They Know2024Benchmark/EvaluationEv CarXiv↗
What is consciousness, and could machines have it2017ApplicationEv CarXiv↗
When Models Know When They Do Not Know - Calibration Cascading and Cleaning2026ApplicationEv CarXiv↗
Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning2025ApplicationEv CarXiv↗
WildBench - Benchmarking LLMs with Challenging Tasks from Real Users in the Wild2024Benchmark/EvaluationEv CarXiv↗
Will artificial agents pursue power by default?2025TheoryEv CarXiv↗
WinoGrande - An Adversarial Winograd Schema Challenge at Scale2019Benchmark/EvaluationEv CarXiv↗
World Models2018ArchitectureEv AarXiv↗
Yi - Open Foundation Models by 01.AI2024ArchitectureEv CarXiv↗
AI 에이전트를 더 똑똑하게 만드는 Context Engineering 프레임워크2024ApplicationEv CarXiv↗
KDD 2026 Paper Review—ApplicationEv Unknown—
Review - DT-MDP-CE Framework (KDD'26 Under Review)2024ApplicationEv CarXiv↗
CCQ - An LLM-Curated Child Care Quality Dataset to Support AI Research for Children's Health2026ApplicationEv CarXiv↗
KDD 2026 Paper Review—DatasetEv Unknown—
Review - CCQ Dataset (KDD'26 D&B Track)2024ApplicationEv CarXiv↗
_benchmarks - _survey-overview—SurveyEv Unknown—
Agents Paper Collection—SurveyEv Unknown—
_survey-overview—SurveyEv Unknown—
llm-intrinsic-drives-survey2026SurveyEv BarXiv↗
llm-self-preservation-survival-framing-survey2026SurveyEv BarXiv↗
survival-analysis-survey2024SurveyEv AarXiv↗
거대 언어 모델(LLM) 에이전트의 행동 지속 동기에 관한 인지과학 및 기계 심리학적 ᄉ—TheoryEv Unknown—
대규모 언어 모델의 자기보존 욕구와 행동 발현 기제 - 자기 결정 이론을 기반으로 하—TheoryEv Unknown—
대형 언어 모델(LLM)의 생존 압박 인지 및 과제 포기 행동의 동기적 기원에 대한 소거—TheoryEv Unknown—
LLMs_Do_Not_Simulate_Human_Psychology_20252025Benchmark/EvaluationEv UnknownarXiv↗
Agentive linguistic framing affects responsibility assignments toward AIs and their creators2025OtherEv UnknownarXiv↗
KoBBQ - Korean Bias Benchmark for Question Answering2024Benchmark/EvaluationEv UnknownarXiv↗
White Matter Integrity, Creativity, and Psychopathology - Disentangling Constructs with Diffusion Tensor Imaging2010OtherEv UnknownarXiv↗
AI ageism and its consequence - Benevolent ageist attitudes expressed byLLMs could reinforce ageism in humans2025OtherEv UnknownarXiv↗
Age and Gender Related Differences in Speech Alignment = Toward Humans and Voice-AI2021OtherEv UnknownarXiv↗
Artificial intelligence and moral dilemmas - Perception of ethical decision-making in AI2022OtherEv UnknownarXiv↗
Effects of emotional content on social inhibition of gaze in live social and non‑social situations2023OtherEv UnknownarXiv↗
How human–AI feedback loops alter human perceptual, emotional and social judgements2024OtherEv UnknownarXiv↗
Large language models are pro solving and creating emotional intelligence tests2025OtherEv UnknownarXiv↗
More human than human - measuring ChatGPT political bias2024OtherEv UnknownarXiv↗
Trust in an AI versus a Human teammate - The effects of teammate identity and performance on Human-AI cooperation2023OtherEv UnknownarXiv↗
When communicative AIs are cooperative actors - a prisoner's dilemma experiment on human-communicative artificial intelligence cooperation2023OtherEv UnknownarXiv↗