{"total":15,"rows":[{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2511.02108","title":"Metamorphic Testing of Large Language Models for Natural Language Processing","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2602.02888","title":"HALT: Hallucination Assessment via Log-probs as Time series","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2605.24919","title":"MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2512.23547","title":"Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2508.10192","title":"Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2508.18473","title":"Principled Detection of Hallucinations in Large Language Models via Multiple Testing","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2606.08157","title":"Cross Paraphrastic Invariance Learning for Hallucination Detection","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.08158","title":"Constrained Paraphrase Consistency for LLM Hallucination Detection","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.21517","title":"MedHal-Loc: Are \"Explainable-by-Architecture\" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}