MILE:情境学习系统的突变测试框架

Zeming Wei, Yihao Zhang, Meng Sun
{"title":"MILE:情境学习系统的突变测试框架","authors":"Zeming Wei, Yihao Zhang, Meng Sun","doi":"arxiv-2409.04831","DOIUrl":null,"url":null,"abstract":"In-context Learning (ICL) has achieved notable success in the applications of\nlarge language models (LLMs). By adding only a few input-output pairs that\ndemonstrate a new task, the LLM can efficiently learn the task during inference\nwithout modifying the model parameters. Such mysterious ability of LLMs has\nattracted great research interests in understanding, formatting, and improving\nthe in-context demonstrations, while still suffering from drawbacks like\nblack-box mechanisms and sensitivity against the selection of examples. In this\nwork, inspired by the foundations of adopting testing techniques in machine\nlearning (ML) systems, we propose a mutation testing framework designed to\ncharacterize the quality and effectiveness of test data for ICL systems. First,\nwe propose several mutation operators specialized for ICL demonstrations, as\nwell as corresponding mutation scores for ICL test sets. With comprehensive\nexperiments, we showcase the effectiveness of our framework in evaluating the\nreliability and quality of ICL test suites. Our code is available at\nhttps://github.com/weizeming/MILE.","PeriodicalId":501278,"journal":{"name":"arXiv - CS - Software Engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MILE: A Mutation Testing Framework of In-Context Learning Systems\",\"authors\":\"Zeming Wei, Yihao Zhang, Meng Sun\",\"doi\":\"arxiv-2409.04831\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In-context Learning (ICL) has achieved notable success in the applications of\\nlarge language models (LLMs). By adding only a few input-output pairs that\\ndemonstrate a new task, the LLM can efficiently learn the task during inference\\nwithout modifying the model parameters. Such mysterious ability of LLMs has\\nattracted great research interests in understanding, formatting, and improving\\nthe in-context demonstrations, while still suffering from drawbacks like\\nblack-box mechanisms and sensitivity against the selection of examples. In this\\nwork, inspired by the foundations of adopting testing techniques in machine\\nlearning (ML) systems, we propose a mutation testing framework designed to\\ncharacterize the quality and effectiveness of test data for ICL systems. First,\\nwe propose several mutation operators specialized for ICL demonstrations, as\\nwell as corresponding mutation scores for ICL test sets. With comprehensive\\nexperiments, we showcase the effectiveness of our framework in evaluating the\\nreliability and quality of ICL test suites. Our code is available at\\nhttps://github.com/weizeming/MILE.\",\"PeriodicalId\":501278,\"journal\":{\"name\":\"arXiv - CS - Software Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Software Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.04831\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Software Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04831","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

上下文学习(ICL)在大型语言模型(LLM)的应用中取得了显著的成功。LLM 只需添加几个能演示新任务的输入输出对,就能在推理过程中高效地学习任务,而无需修改模型参数。LLMs 的这种神秘能力在理解、格式化和改进上下文演示方面吸引了大量的研究兴趣,但仍存在黑箱机制和对示例选择敏感等缺点。在这项工作中,受机器学习(ML)系统中采用测试技术的基础启发,我们提出了一个突变测试框架,旨在描述 ICL 系统测试数据的质量和有效性。首先,我们提出了几种专门用于 ICL 演示的突变算子,以及用于 ICL 测试集的相应突变分数。通过综合实验,我们展示了我们的框架在评估 ICL 测试套件的可靠性和质量方面的有效性。我们的代码可在https://github.com/weizeming/MILE。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
MILE: A Mutation Testing Framework of In-Context Learning Systems
In-context Learning (ICL) has achieved notable success in the applications of large language models (LLMs). By adding only a few input-output pairs that demonstrate a new task, the LLM can efficiently learn the task during inference without modifying the model parameters. Such mysterious ability of LLMs has attracted great research interests in understanding, formatting, and improving the in-context demonstrations, while still suffering from drawbacks like black-box mechanisms and sensitivity against the selection of examples. In this work, inspired by the foundations of adopting testing techniques in machine learning (ML) systems, we propose a mutation testing framework designed to characterize the quality and effectiveness of test data for ICL systems. First, we propose several mutation operators specialized for ICL demonstrations, as well as corresponding mutation scores for ICL test sets. With comprehensive experiments, we showcase the effectiveness of our framework in evaluating the reliability and quality of ICL test suites. Our code is available at https://github.com/weizeming/MILE.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing Motivations, Challenges, Best Practices, and Benefits for Bots and Conversational Agents in Software Engineering: A Multivocal Literature Review A Taxonomy of Self-Admitted Technical Debt in Deep Learning Systems Investigating team maturity in an agile automotive reorganization
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1