{"total":16,"rows":[{"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":"2602.01031","title":"HalluHard: A Hard Multi-Turn Hallucination Benchmark","created":"2026-02-01","cited_by_count":9,"area":null},{"id":"2510.19318","title":"HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2511.19872","title":"Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2605.31483","title":"BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2505.03030","title":"UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2506.13990","title":"Machine Mirages: Defining the Undefined","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2508.00889","title":"FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2510.10539","title":"Detecting Hallucinations in Authentic LLM-Human Interactions","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2601.01401","title":"LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2608.00205","title":"Averaging Bias: Human Faithfulness Annotations are not Locally Faithful","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03655","title":"Decoupling Generation and Selection for Budget-Constrained Faithful Summarization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.03580","title":"HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.39229","title":"RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}