{"total":31,"rows":[{"id":"2410.16090","title":"Analysing the Residual Stream of Language Models Under Knowledge Conflicts","created":"2024-10-21","cited_by_count":17,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2505.22787","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2503.23361","title":"Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base","created":"2025-03-30","cited_by_count":6,"area":null},{"id":"2505.21608","title":"How does Misinformation Affect Large Language Model Behaviors and Preferences?","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2508.12355","title":"Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-Answering","created":"2025-08-17","cited_by_count":5,"area":null},{"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":"2601.11886","title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence","created":"2026-01-17","cited_by_count":3,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2510.07926","title":"Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.19172","title":"When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2603.15892","title":"Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.23750","title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","created":"2026-04-26","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":"2505.21958","title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.11967","title":"MillStone: How Open-Minded Are LLMs?","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2511.10881","title":"A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2602.14065","title":"REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.20245","title":"Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.16019","title":"Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2609.01852","title":"The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.30813","title":"A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2501.01332","title":"Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2510.17890","title":"MIN-Merging: Merge the Important Neurons for Model Merging","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2601.11232","title":"FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2607.24117","title":"Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems","created":"2026-07-27","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":"2608.28478","title":"Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.39473","title":"Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}