{"total":23,"rows":[{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2602.01031","title":"HalluHard: A Hard Multi-Turn Hallucination Benchmark","created":"2026-02-01","cited_by_count":9,"area":null},{"id":"2506.06091","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2504.19061","title":"Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models","created":"2025-04-27","cited_by_count":4,"area":null},{"id":"2607.09880","title":"CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series","created":"2026-07-10","cited_by_count":4,"area":null},{"id":"2510.25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2504.08596","title":"MedHal: a Synthetic Dataset for Medical Hallucination Detection","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.07209","title":"Hallucination Detection via Activations of Open-Weight Proxy Analyzers","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.17007","title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2603.20252","title":"FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2606.01301","title":"Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2603.05184","title":"Logi-PAR: Logic-Infused Patient Activity Recognition via Differentiable Rule","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.06028","title":"A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.04893","title":"Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.22963","title":"Graph Alignment Topology as an Inductive Bias for Grounding Detection","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.00919","title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.05170","title":"ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.24155","title":"MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.13003","title":"Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.14825","title":"Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection","created":"2026-09-13","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}