{"total":15,"rows":[{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2601.13384","title":"From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning","created":"2026-01-19","cited_by_count":6,"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":"2506.00204","title":"Structure-Aware Fill-in-the-Middle Pretraining for Code","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2502.15243","title":"Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","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":"2508.15229","title":"VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.05788","title":"Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2505.18789","title":"From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2601.15879","title":"Evaluating and Achieving Controllable Code Completion in Code LLM","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2410.18107","title":"In-Context Code-Text Learning for Bimodal Software Engineering","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2606.03130","title":"Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.08676","title":"Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2609.36952","title":"ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}