{"list":"other","total":51,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73},{"id":"2308.10335","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","created":"2023-08-20","cited_by_count":73},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53},{"id":"2408.16498","title":"A Survey on Evaluating Large Language Models in Code Generation Tasks","created":"2024-08-29","cited_by_count":44},{"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},{"id":"2305.11248","title":"Investigating and Designing for Trust in AI-powered Code Generation Tools","created":"2023-05-18","cited_by_count":34},{"id":"2407.07565","title":"On Leakage of Code Generation Evaluation Datasets","created":"2024-07-10","cited_by_count":32},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32},{"id":"2401.15232","title":"How Beginning Programmers and Code LLMs (Mis)read Each Other","created":"2024-01-26","cited_by_count":31},{"id":"2401.16186","title":"An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project","created":"2024-01-29","cited_by_count":28},{"id":"2402.08030","title":"Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking","created":"2024-02-12","cited_by_count":26},{"id":"2305.15377","title":"Uncovering and Quantifying Social Biases in Code Generation","created":"2023-05-24","cited_by_count":25},{"id":"2411.10351","title":"Bias Unveiled: Investigating Social Bias in LLM-Generated Code","created":"2024-11-15","cited_by_count":25},{"id":"2206.13179","title":"AixBench: A Code Generation Benchmark Dataset","created":"2022-06-27","cited_by_count":22},{"id":"2307.07367","title":"Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow","created":"2023-07-14","cited_by_count":22},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20},{"id":"2502.07776","title":"Auditing Prompt Caching in Language Model APIs","created":"2025-02-11","cited_by_count":20},{"id":"2406.12513","title":"Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs","created":"2024-06-18","cited_by_count":19},{"id":"2404.19368","title":"Exploring Multi-Lingual Bias of Large Code Models in Code Generation","created":"2024-04-30","cited_by_count":17},{"id":"2503.16508","title":"Conversational AI as a Coding Assistant: Understanding Programmers' Interactions with and Expectations from Large Language Models for Coding","created":"2025-03-14","cited_by_count":11},{"id":"2402.19431","title":"Compositional API Recommendation for Library-Oriented Code Generation","created":"2024-02-29","cited_by_count":10},{"id":"2501.07849","title":"The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation","created":"2025-01-14","cited_by_count":10},{"id":"2501.13122","title":"Zero-Shot Verification-guided Chain of Thoughts","created":"2025-01-21","cited_by_count":10},{"id":"2005.12574","title":"Selecting third-party libraries: The practitioners' perspective","created":"2020-05-26","cited_by_count":9},{"id":"2401.03855","title":"PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs","created":"2024-01-08","cited_by_count":9},{"id":"2403.10468","title":"An Empirical Study on Developers Shared Conversations with ChatGPT in GitHub Pull Requests and Issues","created":"2024-03-15","cited_by_count":9},{"id":"2402.09299","title":"Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code","created":"2024-02-14","cited_by_count":8},{"id":"2502.17450","title":"Studying How Configurations Impact Code Generation in LLMs: the Case of ChatGPT","created":"2025-02-07","cited_by_count":8},{"id":"2301.09789","title":"A Qualitative Study on the Implementation Design Decisions of Developers","created":"2023-01-24","cited_by_count":7},{"id":"2408.05128","title":"Is ChatGPT a Good Software Librarian? An Exploratory Study on the Use of ChatGPT for Software Library Recommendations","created":"2024-08-09","cited_by_count":7},{"id":"2409.13178","title":"A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How","created":"2024-09-20","cited_by_count":7},{"id":"2301.07524","title":"Towards Causal Analysis of Empirical Software Engineering Data: The Impact of Programming Languages on Coding Competitions","created":"2023-01-18","cited_by_count":4},{"id":"2107.11912","title":"Performance vs Programming Effort between Rust and C on Multicore Architectures: Case Study in N-Body","created":"2021-07-26","cited_by_count":2},{"id":"1402.1188","title":"On Designing Better Tools for Learning APIs","created":"2014-02-05","cited_by_count":1}],"next_cursor":null}