{"total":32,"rows":[{"id":"2502.14302","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","created":"2025-02-20","cited_by_count":34,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"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":"2504.05324","title":"Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2507.08203","title":"TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2604.23588","title":"FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification","created":"2026-04-26","cited_by_count":4,"area":null},{"id":"2505.00506","title":"HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2603.18014","title":"Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2505.06698","title":"SCAN: Structured Capability Assessment and Navigation for LLMs","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2505.14101","title":"MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2601.21969","title":"Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2410.08764","title":"Measuring the Groundedness of Legal Question-Answering Systems","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2411.03300","title":"VERITAS: A Unified Approach to Reliability Evaluation","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2411.03920","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2504.14429","title":"ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations","created":"2025-04-20","cited_by_count":1,"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":"2510.21118","title":"The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.08916","title":"HalluClean: A Unified Framework to Combat Hallucinations in LLMs","created":"2025-11-12","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":"2602.22787","title":"Probing for Knowledge Attribution in Large Language Models","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.16045","title":"POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2412.12148","title":"How to Choose a Threshold for an Evaluation Metric for Large Language Models","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2507.00579","title":"TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2605.25376","title":"KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.08705","title":"Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.26807","title":"KARLA: Knowledge-base Augmented Retrieval for Language Models","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}