{"total":81,"rows":[{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80,"area":null},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2406.00799","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","created":"2024-06-02","cited_by_count":72,"area":"rag"},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2403.01548","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","created":"2024-03-03","cited_by_count":45,"area":null},{"id":"2403.20009","title":"On Large Language Models' Hallucination with Regard to Known Facts","created":"2024-03-29","cited_by_count":43,"area":null},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2311.15131","title":"Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching","created":"2023-11-25","cited_by_count":24,"area":"mechinterp"},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2502.08767","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","created":"2025-02-12","cited_by_count":18,"area":null},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2502.14634","title":"CER: Confidence Enhanced Reasoning in LLMs","created":"2025-02-20","cited_by_count":17,"area":"lr"},{"id":"2405.03205","title":"Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions","created":"2024-05-06","cited_by_count":15,"area":"mechinterp"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"id":"2503.13804","title":"Empowering GraphRAG with Knowledge Filtering and Integration","created":"2025-03-18","cited_by_count":15,"area":null},{"id":"2410.20210","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","created":"2024-10-26","cited_by_count":12,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2507.13868","title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","created":"2025-07-18","cited_by_count":11,"area":"mllm"},{"id":"2502.02173","title":"Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge","created":"2025-02-04","cited_by_count":10,"area":null},{"id":"2505.18752","title":"Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning","created":"2025-05-24","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2406.11890","title":"Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2312.16374","title":"LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis","created":"2023-12-27","cited_by_count":7,"area":null},{"id":"2502.03199","title":"Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2602.03664","title":"Mitigating Conversational Inertia in Multi-Turn Agents","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2505.12636","title":"Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2404.00884","title":"Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2503.09029","title":"DAST: Difficulty-Aware Self-Training on Large Language Models","created":"2025-03-12","cited_by_count":3,"area":"synth"},{"id":"2505.19606","title":"Languages in Whisper-Style Speech Encoders Align Both Phonetically and Semantically","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2510.02480","title":"Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting","created":"2025-10-02","cited_by_count":3,"area":"inference"},{"id":"2510.04108","title":"Can Linear Probes Measure LLM Uncertainty?","created":"2025-10-05","cited_by_count":3,"area":"mechinterp"},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2507.07731","title":"Energy-Guided Decoding for Object Hallucination Mitigation","created":"2025-07-10","cited_by_count":2,"area":"mllm"},{"id":"2507.09875","title":"Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2509.24164","title":"Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2603.04464","title":"Understanding the Dynamics of Demonstration Conflict in In-Context Learning","created":"2026-03-03","cited_by_count":2,"area":"mechinterp"},{"id":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2606.11205","title":"Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention","created":"2026-04-22","cited_by_count":2,"area":"mechinterp"},{"id":"2408.01935","title":"Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2602.07778","title":"Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs","created":"2026-02-08","cited_by_count":1,"area":"inference"},{"id":"2606.01845","title":"Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2607.04640","title":"Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models","created":"2026-07-06","cited_by_count":1,"area":"alignment"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"},{"id":"2507.17618","title":"SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token","created":"2025-07-23","cited_by_count":0,"area":"inference"},{"id":"2601.17082","title":"Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models","created":"2026-01-23","cited_by_count":0,"area":"mllm"},{"id":"2602.13567","title":"DistillLens: Symmetric Knowledge Distillation Through Logit Lens","created":"2026-02-14","cited_by_count":0,"area":"mechinterp"},{"id":"2603.13911","title":"On the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.09885","title":"What do your logits know?","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.12426","title":"Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2604.22565","title":"Learning Evidence Highlighting for Frozen LLMs","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.03052","title":"How Language Models Process Negation","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.08295","title":"In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification","created":"2026-05-08","cited_by_count":0,"area":"mechinterp"},{"id":"2605.20382","title":"Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.20508","title":"What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?","created":"2026-06-18","cited_by_count":0,"area":"alignment"},{"id":"2606.22473","title":"Interleaved Speech Language Models Latently Work In Text","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.26100","title":"TSS: Target-Side Sparsification for Speculative Decoding in Domain-Specific Large Language Models","created":"2026-08-15","cited_by_count":0,"area":"inference"},{"id":"2610.02702","title":"Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.15314","title":"Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}