{"total":96,"rows":[{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369,"area":"rag"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2407.07071","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","created":"2024-07-09","cited_by_count":142,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2402.14409","title":"Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models","created":"2024-02-22","cited_by_count":93,"area":"rag"},{"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":"2312.09979","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","created":"2023-12-15","cited_by_count":82,"area":"moe"},{"id":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"area":null},{"id":"2305.01579","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","created":"2023-05-02","cited_by_count":54,"area":"rag"},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"id":"2405.02750","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","created":"2024-05-04","cited_by_count":49,"area":null},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2406.08702","title":"VLind-Bench: Measuring Language Priors in Large Vision-Language Models","created":"2024-06-13","cited_by_count":45,"area":"mllm"},{"id":"2310.14393","title":"Merging Generated and Retrieved Knowledge for Open-Domain QA","created":"2023-10-22","cited_by_count":36,"area":null},{"id":"2407.17023","title":"DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models","created":"2024-07-24","cited_by_count":34,"area":null},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2310.01779","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","created":"2023-10-03","cited_by_count":32,"area":"mllm"},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2502.21228","title":"ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer","created":"2025-02-28","cited_by_count":29,"area":null},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2402.11893","title":"Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2402.11924","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","created":"2024-02-19","cited_by_count":27,"area":"lr"},{"id":"2305.14010","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","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":"2410.15737","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","created":"2024-10-21","cited_by_count":21,"area":"rag"},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","cited_by_count":18,"area":null},{"id":"2408.03247","title":"Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons","created":"2024-08-06","cited_by_count":16,"area":null},{"id":"2311.09053","title":"Assessing Knowledge Editing in Language Models via Relation Perspective","created":"2023-11-15","cited_by_count":15,"area":null},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2408.01419","title":"DebateQA: Evaluating Question Answering on Debatable Knowledge","created":"2024-08-02","cited_by_count":12,"area":null},{"id":"2410.05801","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2309.08594","title":"\"Merge Conflicts!\" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2409.08435","title":"When Context Leads but Parametric Memory Follows in Large Language Models","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2409.10955","title":"Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style","created":"2024-09-17","cited_by_count":11,"area":"rag"},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"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":"2410.06913","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","created":"2024-10-09","cited_by_count":10,"area":"safety"},{"id":"2511.14342","title":"ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions","created":"2025-11-18","cited_by_count":10,"area":null},{"id":"2601.07767","title":"Are LLM Decisions Faithful to Verbal Confidence?","created":"2026-01-12","cited_by_count":8,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2310.13505","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2401.18001","title":"Desiderata for the Context Use of Question Answering Systems","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2402.01453","title":"The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2410.02499","title":"Defining Knowledge: Bridging Epistemology and Large Language Models","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2310.19347","title":"Improving Factual Consistency of News Summarization by Contrastive Preference Optimization","created":"2023-10-30","cited_by_count":6,"area":"alignment"},{"id":"2408.04414","title":"Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning","created":"2024-08-08","cited_by_count":6,"area":"rag"},{"id":"2505.12543","title":"Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey","created":"2025-05-18","cited_by_count":6,"area":"agents"},{"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":"2507.19477","title":"Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts","created":"2025-07-25","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":"2408.10490","title":"Analysis of Plan-based Retrieval for Grounded Text Generation","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2410.15667","title":"RAC: Efficient LLM Factuality Correction with Retrieval Augmentation","created":"2024-10-21","cited_by_count":5,"area":"rag"},{"id":"2412.07923","title":"Asking Again and Again: Exploring LLM Robustness to Repeated Questions","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","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":"2403.14578","title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2406.13929","title":"Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2410.16843","title":"Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning","created":"2024-10-22","cited_by_count":4,"area":"rag"},{"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":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.11886","title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence","created":"2026-01-17","cited_by_count":3,"area":null},{"id":"2602.22771","title":"ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2502.13836","title":"Quantifying Memorization and Parametric Response Rates in Retrieval-Augmented Vision-Language Models","created":"2025-02-19","cited_by_count":2,"area":"mllm"},{"id":"2502.14908","title":"SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2502.19779","title":"Do Retrieval-Augmented Language Models Adapt to Varying User Needs?","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2605.12185","title":"Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2402.15162","title":"Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2407.13048","title":"Establishing Knowledge Preference in Language Models","created":"2024-07-17","cited_by_count":1,"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":"2608.22856","title":"Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA","created":"2026-08-24","cited_by_count":1,"area":"rag"},{"id":"2608.26295","title":"MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2403.01461","title":"Answerability in Retrieval-Augmented Open-Domain Question Answering","created":"2024-03-03","cited_by_count":0,"area":"rag"},{"id":"2506.20989","title":"Can Gradient Descent Simulate Prompting?","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2510.20543","title":"The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2602.01451","title":"Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.23659","title":"Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.19782","title":"KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.05686","title":"Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2609.35475","title":"Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37491","title":"Regime Boundary Alignment for Evidence-Gated Question Answering","created":"2026-09-25","cited_by_count":0,"area":"rag"},{"id":"2609.37499","title":"Who Warmed the Archives? LLMs Overestimate Historical Warmth","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.04691","title":"RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation","created":"2026-10-03","cited_by_count":0,"area":"rag"},{"id":"2610.12837","title":"COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.15677","title":"Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}