Saved in:
Bibliographic Details
Main Authors: Gong, Jing, Wu, Yanghui, Liang, Linxi, Wang, Yanlin, Chen, Jiachi, Liu, Mingwei, Zheng, Zibin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.11589
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918321680547840
author Gong, Jing
Wu, Yanghui
Liang, Linxi
Wang, Yanlin
Chen, Jiachi
Liu, Mingwei
Zheng, Zibin
author_facet Gong, Jing
Wu, Yanghui
Liang, Linxi
Wang, Yanlin
Chen, Jiachi
Liu, Mingwei
Zheng, Zibin
contents Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who assess code primarily through semantic understanding rather than functional verification, leading to potential inaccuracies and scalability issues. Additionally, current evaluation metrics often overlook the multi-choice nature of code search. This paper introduces CoSQA+, pairing high-quality queries from CoSQA with multiple suitable codes. We develop an automated pipeline featuring multiple model-based candidate selections and the novel test-driven agent annotation system. Among a single Large Language Model (LLM) annotator and Python expert annotators (without test-based verification), agents leverage test-based verification and achieve the highest accuracy of 93.9%. Through extensive experiments, CoSQA+ has demonstrated superior quality over CoSQA. Models trained on CoSQA+ exhibit improved performance. We publicly release both CoSQA+_all, which contains 412,080 agent-annotated pairs, and CoSQA+_verified, which contains 1,000 human-verified pairs, at https://github.com/DeepSoftwareAnalytics/CoSQA_Plus.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11589
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents
Gong, Jing
Wu, Yanghui
Liang, Linxi
Wang, Yanlin
Chen, Jiachi
Liu, Mingwei
Zheng, Zibin
Software Engineering
Artificial Intelligence
Information Retrieval
I.2.7; D.2.3
Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who assess code primarily through semantic understanding rather than functional verification, leading to potential inaccuracies and scalability issues. Additionally, current evaluation metrics often overlook the multi-choice nature of code search. This paper introduces CoSQA+, pairing high-quality queries from CoSQA with multiple suitable codes. We develop an automated pipeline featuring multiple model-based candidate selections and the novel test-driven agent annotation system. Among a single Large Language Model (LLM) annotator and Python expert annotators (without test-based verification), agents leverage test-based verification and achieve the highest accuracy of 93.9%. Through extensive experiments, CoSQA+ has demonstrated superior quality over CoSQA. Models trained on CoSQA+ exhibit improved performance. We publicly release both CoSQA+_all, which contains 412,080 agent-annotated pairs, and CoSQA+_verified, which contains 1,000 human-verified pairs, at https://github.com/DeepSoftwareAnalytics/CoSQA_Plus.
title CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents
topic Software Engineering
Artificial Intelligence
Information Retrieval
I.2.7; D.2.3
url https://arxiv.org/abs/2406.11589