{"total":54,"rows":[{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2508.13333","title":"HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design","created":"2025-08-18","cited_by_count":16,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","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":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2601.01129","title":"RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian","created":"2026-01-03","cited_by_count":6,"area":null},{"id":"2507.21285","title":"Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2510.08005","title":"Past, Present, and Future of Bug Tracking in the Generative AI Era","created":"2025-10-09","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":"2502.19149","title":"Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval","created":"2025-02-26","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":"2508.11257","title":"Hallucination in LLM-Based Code Generation: An Automotive Case Study","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2511.19422","title":"SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2603.13251","title":"ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2604.27643","title":"HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2504.01248","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2505.09724","title":"An AI-Powered Research Assistant in the Lab: A Practical Guide for Text Analysis Through Iterative Collaboration with LLMs","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.12621","title":"SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2508.02773","title":"Web3 x AI Agents: Landscape, Integrations, and Foundational Challenges","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.20277","title":"Investigating Security Implications of Automatically Generated Code on the Software Supply Chain","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.22210","title":"LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2511.19875","title":"CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2603.26359","title":"Automated near-term quantum algorithm discovery for molecular ground states","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.08963","title":"Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.10126","title":"MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis","created":"2026-04-11","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":"2605.06279","title":"Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2509.02581","title":"Charting the Future of Scholarly Knowledge with AI: A Community Perspective","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.10290","title":"Grounded AI for Code Review: Resource-Efficient Large-Model Serving in Enterprise Pipelines","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.15917","title":"Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2601.02504","title":"Enhancing Debugging Skills with AI-Powered Assistance: A Real-Time Tool for Debugging Support","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2603.04631","title":"Towards automated data analysis: A guided framework for LLM-based risk estimation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.00014","title":"Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses","created":"2026-03-10","cited_by_count":0,"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":"2604.26961","title":"Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding","created":"2026-04-09","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":"2605.24137","title":"Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25658","title":"AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization","created":"2026-05-25","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":"2607.08981","title":"The Patchwork Problem in LLM-Generated Code","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18280","title":"Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.26220","title":"Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.01601","title":"Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation","created":"2026-09-01","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},{"id":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31908","title":"Improving Medical Calculation of LLMs with Embedded Coding","created":"2026-09-25","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}