{"total":116,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2402.09497","title":"Instruction Tuning for Secure Code Generation","created":"2024-02-14","cited_by_count":68,"area":null},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2308.09895","title":"Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs","created":"2023-08-19","cited_by_count":45,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2407.10424","title":"CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization","created":"2024-07-15","cited_by_count":38,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32,"area":null},{"id":"2405.07883","title":"Zero-Shot Tokenizer Transfer","created":"2024-05-13","cited_by_count":31,"area":null},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2406.14712","title":"Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2405.19495","title":"Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code","created":"2024-05-29","cited_by_count":25,"area":null},{"id":"2402.08699","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness","created":"2024-02-13","cited_by_count":23,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2501.04694","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","created":"2025-01-08","cited_by_count":20,"area":null},{"id":"2309.05454","title":"Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models","created":"2023-09-11","cited_by_count":17,"area":null},{"id":"2410.10209","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2502.01619","title":"Learning to Generate Unit Tests for Automated Debugging","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2503.20807","title":"Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models","created":"2025-03-24","cited_by_count":17,"area":null},{"id":"2403.06095","title":"RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion","created":"2024-03-10","cited_by_count":15,"area":null},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2402.05980","title":"Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2404.07940","title":"InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models","created":"2024-03-11","cited_by_count":13,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.01296","title":"Speculative Coreset Selection for Task-Specific Fine-tuning","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2410.05357","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2403.05188","title":"CommitBench: A Benchmark for Commit Message Generation","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2401.07870","title":"JumpCoder: Go Beyond Autoregressive Coder via Online Modification","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2410.02749","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2411.05046","title":"PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training","created":"2024-11-07","cited_by_count":7,"area":null},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2501.18784","title":"Successor-Generator Planning with LLM-generated Heuristics","created":"2025-01-30","cited_by_count":7,"area":null},{"id":"2505.02931","title":"The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2405.20179","title":"Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2406.06864","title":"Validating LLM-Generated Programs with Metamorphic Prompt Testing","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2412.03398","title":"RedStone: Curating General, Code, Math, and QA Data for Large Language Models","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2308.15645","title":"AskIt: Unified Programming Interface for Programming with Large Language Models","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2402.09615","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2406.14887","title":"InternLM-Law: An Open Source Chinese Legal Large Language Model","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2503.08823","title":"ResBench: Benchmarking LLM-Generated FPGA Designs with Resource Awareness","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2405.14619","title":"exLong: Generating Exceptional Behavior Tests with Large Language Models","created":"2024-05-23","cited_by_count":4,"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":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2511.04234","title":"Reusing Pre-Training Data at Test Time is a Compute Multiplier","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2311.17972","title":"Self-Infilling Code Generation","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2405.19032","title":"Large Language Models for Code Summarization","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2406.09891","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2410.14740","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2410.18957","title":"Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2501.08496","title":"Quantifying the Importance of Data Alignment in Downstream Model Performance","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2406.07084","title":"Leveraging Large Language Models for Efficient Failure Analysis in Game Development","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2503.09020","title":"Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2505.18011","title":"Training with Pseudo-Code for Instruction Following","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2511.09900","title":"Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2607.02469","title":"TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.25130","title":"Learning from 53.6K Real-World Developer Edits of AI-Generated Code","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2403.15426","title":"CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2405.19250","title":"Kotlin ML Pack: Technical Report","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2408.09134","title":"Better Python Programming for all: With the focus on Maintainability","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2408.09568","title":"MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair","created":"2024-08-18","cited_by_count":0,"area":null}],"next_cursor":"100"}