{"total":24,"rows":[{"id":"2406.13890","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","created":"2024-06-19","cited_by_count":28,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"area":null},{"id":"2407.04831","title":"Code Hallucination","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2601.19072","title":"HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation","created":"2026-01-27","cited_by_count":5,"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":"2508.08661","title":"Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics","created":"2025-08-12","cited_by_count":4,"area":null},{"id":"2607.01883","title":"PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation","created":"2026-07-02","cited_by_count":4,"area":null},{"id":"2605.28500","title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2506.11021","title":"Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.11257","title":"Hallucination in LLM-Based Code Generation: An Automotive Case Study","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.22202","title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2604.10520","title":"ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization","created":"2026-04-12","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":"2604.17351","title":"SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization","created":"2026-04-19","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":"2606.25402","title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.18357","title":"Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.06041","title":"LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.07779","title":"CodeTD: Topology of Attention Detects Hallucinations in Code LLMs","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.03080","title":"MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}