{"total":91,"rows":[{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2403.18167","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","created":"2024-03-27","cited_by_count":38,"area":null},{"id":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35,"area":null},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32,"area":"mllm"},{"id":"2503.10996","title":"Taming Knowledge Conflicts in Language Models","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2406.16033","title":"Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models","created":"2024-06-23","cited_by_count":22,"area":"mechinterp"},{"id":"2506.06485","title":"Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict","created":"2025-06-06","cited_by_count":16,"area":null},{"id":"2506.07171","title":"RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality","created":"2025-06-08","cited_by_count":16,"area":"safety"},{"id":"2408.00137","title":"Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment","created":"2024-07-31","cited_by_count":12,"area":null},{"id":"2409.07497","title":"OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11,"area":"rag"},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","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":"2510.23451","title":"Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences","created":"2025-10-27","cited_by_count":11,"area":"alignment"},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2504.13562","title":"DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification","created":"2025-04-18","cited_by_count":10,"area":"safety"},{"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":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2402.19103","title":"Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2412.17031","title":"A Reality Check on Context Utilisation for Retrieval-Augmented Generation","created":"2024-12-22","cited_by_count":9,"area":"rag"},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2505.15865","title":"How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads","created":"2025-05-21","cited_by_count":9,"area":"mllm"},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2410.11469","title":"O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2406.00944","title":"A Theory for Token-Level Harmonization in Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":7,"area":"rag"},{"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":"2409.13202","title":"CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance","created":"2024-09-20","cited_by_count":6,"area":"agents"},{"id":"2505.09338","title":"Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs","created":"2025-05-14","cited_by_count":6,"area":null},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2601.06842","title":"Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation","created":"2026-01-11","cited_by_count":6,"area":"rag"},{"id":"2409.15820","title":"Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns","created":"2024-09-24","cited_by_count":5,"area":null},{"id":"2601.09445","title":"Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2602.19969","title":"ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2504.12982","title":"Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild","created":"2025-04-17","cited_by_count":4,"area":"rag"},{"id":"2505.11995","title":"Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation","created":"2025-05-17","cited_by_count":4,"area":"rag"},{"id":"2505.16518","title":"CUB: Benchmarking Context Utilisation Techniques for Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2505.23277","title":"Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression","created":"2025-05-29","cited_by_count":4,"area":"rag"},{"id":"2508.15793","title":"Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2510.02370","title":"How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2602.04288","title":"Contextual Drag: How Errors in the Context Affect LLM Reasoning","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2509.01787","title":"AHAMask: Reliable Task Specification for Large Audio Language Models without Instructions","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2602.02467","title":"Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2604.11322","title":"Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2606.27786","title":"SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation","created":"2026-06-26","cited_by_count":3,"area":"rag"},{"id":"2606.28273","title":"Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models","created":"2026-06-26","cited_by_count":3,"area":"mllm"},{"id":"2406.12416","title":"Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models","created":"2024-06-18","cited_by_count":2,"area":"alignment"},{"id":"2506.05278","title":"Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"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":"2512.04545","title":"EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2603.03335","title":"Compressed Sensing for Capability Localization in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2605.11574","title":"Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.30219","title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2502.13648","title":"UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2504.15630","title":"Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2509.10663","title":"Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.18762","title":"When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2601.06599","title":"How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2601.12075","title":"To Copy or Not to Copy: Copying Is Easier to Induce Than Recall","created":"2026-01-17","cited_by_count":1,"area":"rag"},{"id":"2608.12218","title":"Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.00293","title":"Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts","created":"2026-08-31","cited_by_count":1,"area":"mllm"},{"id":"2609.38810","title":"CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models","created":"2026-09-30","cited_by_count":1,"area":"mllm"},{"id":"2505.24292","title":"Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.11390","title":"Medical Interpretability and Knowledge Maps of Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2510.19116","title":"That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.23989","title":"CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction","created":"2026-03-25","cited_by_count":0,"area":"rag"},{"id":"2604.14172","title":"Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations","created":"2026-03-25","cited_by_count":0,"area":"rag"},{"id":"2606.07555","title":"Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.11138","title":"Attention-Path Fragility as an Uncertainty Signal in Large Language Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.24460","title":"Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25894","title":"From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.25602","title":"Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs","created":"2026-09-22","cited_by_count":0,"area":"mechinterp"},{"id":"2609.31342","title":"Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers","created":"2026-09-25","cited_by_count":0,"area":"rag"},{"id":"2610.00606","title":"Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15677","title":"Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18674","title":"From Relation-Specific Heads to Shared Interventions: Contextual Entrainment in Language Models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20067","title":"Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}