{"total":26,"rows":[{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"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":"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":"2503.02879","title":"Wikipedia in the Era of LLMs: Evolution and Risks","created":"2025-03-04","cited_by_count":4,"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":"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":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"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":"2512.21635","title":"Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations","created":"2025-12-25","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":"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":"2605.02083","title":"EditPropBench: Measuring Factual Edit Propagation in Scientific Manuscripts","created":"2026-05-03","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":"2607.19355","title":"Information Discernment in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2408.00122","title":"A Course Shared Task on Evaluating LLM Output for Clinical Questions","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2512.18601","title":"On Finding Inconsistencies in Documents","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2605.20478","title":"Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.11208","title":"BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.11640","title":"TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.26437","title":"ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence","created":"2026-06-24","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":"2607.28384","title":"When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences","created":"2026-07-30","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":"2609.19155","title":"Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.25303","title":"Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing","created":"2026-09-21","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}