{"total":20,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2502.06185","title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2503.08057","title":"Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2504.12589","title":"Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer","created":"2025-04-17","cited_by_count":4,"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":"2508.18651","title":"Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2512.21635","title":"Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","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":"2504.10167","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.20767","title":"CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2601.07422","title":"Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations","created":"2026-01-12","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":"2608.04570","title":"The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","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":"2509.21104","title":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","created":"2025-09-25","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":"2602.08149","title":"DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries","created":"2026-02-08","cited_by_count":0,"area":null}],"next_cursor":null}