{"total":14,"rows":[{"id":"2503.09347","title":"Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts","created":"2025-03-12","cited_by_count":26,"area":null},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2410.17482","title":"Is artificial intelligence still intelligence? LLMs generalize to novel adjective-noun pairs, but don't mimic the full human distribution","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2412.00239","title":"Generating a Low-code Complete Workflow via Task Decomposition and RAG","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2409.18290","title":"Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses from Closed-Domain LLM vs. Clinical Teams","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2503.16457","title":"Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2601.01836","title":"COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2508.20333","title":"Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2512.16750","title":"Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2410.11450","title":"A Cross-Lingual Statutory Article Retrieval Dataset for Taiwan Legal Studies","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2507.15581","title":"Metric assessment protocol in the context of answer fluctuation on MCQ tasks","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2512.00991","title":"Advancing Academic Chatbots: Evaluation of Non Traditional Outputs","created":"2025-11-30","cited_by_count":0,"area":null}],"next_cursor":null}