{"total":29,"rows":[{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2401.11911","title":"Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?","created":"2024-01-22","cited_by_count":48,"area":null},{"id":"2311.09832","title":"WatME: Towards Lossless Watermarking Through Lexical Redundancy","created":"2023-11-16","cited_by_count":27,"area":null},{"id":"2403.04307","title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","created":"2024-03-07","cited_by_count":27,"area":null},{"id":"2406.07070","title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","created":"2024-06-11","cited_by_count":27,"area":null},{"id":"2406.15718","title":"Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models","created":"2024-06-22","cited_by_count":26,"area":null},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25,"area":null},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2407.04020","title":"LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking","created":"2024-07-04","cited_by_count":19,"area":null},{"id":"2504.17309","title":"CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality","created":"2025-04-24","cited_by_count":19,"area":null},{"id":"2403.00896","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models","created":"2024-03-01","cited_by_count":15,"area":null},{"id":"2503.13503","title":"SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models","created":"2025-03-12","cited_by_count":15,"area":null},{"id":"2410.12869","title":"Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2501.02020","title":"Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection","created":"2025-01-02","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2409.14399","title":"Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations","created":"2024-09-22","cited_by_count":7,"area":null},{"id":"2503.01670","title":"Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization","created":"2025-03-03","cited_by_count":6,"area":null},{"id":"2503.15990","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2509.24120","title":"EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2406.19415","title":"An Analysis of Multilingual FActScore","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2504.01369","title":"LITE: LLM-Impelled efficient Taxonomy Evaluation","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2403.08844","title":"AcademiaOS: Automating Grounded Theory Development in Qualitative Research with Large Language Models","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2503.07170","title":"DeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2505.17380","title":"AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2606.13610","title":"One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.20794","title":"Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}