{"total":14,"rows":[{"id":"2409.19492","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","created":"2024-09-29","cited_by_count":21,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2508.16131","title":"The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2605.07024","title":"Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2502.18468","title":"SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2505.18470","title":"Chemical classification program synthesis using generative artificial intelligence","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2603.16434","title":"From Natural Language to Executable Option Strategies via Large Language Models","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2510.18904","title":"DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2602.20166","title":"ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.16107","title":"RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.25973","title":"Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.14839","title":"Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}