从解释到行动:学生成绩反馈的零起点、理论驱动的 LLM 框架

Vinitra Swamy, Davide Romano, Bhargav Srinivasa Desikan, Oana-Maria Camburu, Tanja Käser
{"title":"从解释到行动:学生成绩反馈的零起点、理论驱动的 LLM 框架","authors":"Vinitra Swamy, Davide Romano, Bhargav Srinivasa Desikan, Oana-Maria Camburu, Tanja Käser","doi":"arxiv-2409.08027","DOIUrl":null,"url":null,"abstract":"Recent advances in eXplainable AI (XAI) for education have highlighted a\ncritical challenge: ensuring that explanations for state-of-the-art AI models\nare understandable for non-technical users such as educators and students. In\nresponse, we introduce iLLuMinaTE, a zero-shot, chain-of-prompts LLM-XAI\npipeline inspired by Miller's cognitive model of explanation. iLLuMinaTE is\ndesigned to deliver theory-driven, actionable feedback to students in online\ncourses. iLLuMinaTE navigates three main stages - causal connection,\nexplanation selection, and explanation presentation - with variations drawing\nfrom eight social science theories (e.g. Abnormal Conditions, Pearl's Model of\nExplanation, Necessity and Robustness Selection, Contrastive Explanation). We\nextensively evaluate 21,915 natural language explanations of iLLuMinaTE\nextracted from three LLMs (GPT-4o, Gemma2-9B, Llama3-70B), with three different\nunderlying XAI methods (LIME, Counterfactuals, MC-LIME), across students from\nthree diverse online courses. Our evaluation involves analyses of explanation\nalignment to the social science theory, understandability of the explanation,\nand a real-world user preference study with 114 university students containing\na novel actionability simulation. We find that students prefer iLLuMinaTE\nexplanations over traditional explainers 89.52% of the time. Our work provides\na robust, ready-to-use framework for effectively communicating hybrid\nXAI-driven insights in education, with significant generalization potential for\nother human-centric fields.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From Explanations to Action: A Zero-Shot, Theory-Driven LLM Framework for Student Performance Feedback\",\"authors\":\"Vinitra Swamy, Davide Romano, Bhargav Srinivasa Desikan, Oana-Maria Camburu, Tanja Käser\",\"doi\":\"arxiv-2409.08027\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent advances in eXplainable AI (XAI) for education have highlighted a\\ncritical challenge: ensuring that explanations for state-of-the-art AI models\\nare understandable for non-technical users such as educators and students. In\\nresponse, we introduce iLLuMinaTE, a zero-shot, chain-of-prompts LLM-XAI\\npipeline inspired by Miller's cognitive model of explanation. iLLuMinaTE is\\ndesigned to deliver theory-driven, actionable feedback to students in online\\ncourses. iLLuMinaTE navigates three main stages - causal connection,\\nexplanation selection, and explanation presentation - with variations drawing\\nfrom eight social science theories (e.g. Abnormal Conditions, Pearl's Model of\\nExplanation, Necessity and Robustness Selection, Contrastive Explanation). We\\nextensively evaluate 21,915 natural language explanations of iLLuMinaTE\\nextracted from three LLMs (GPT-4o, Gemma2-9B, Llama3-70B), with three different\\nunderlying XAI methods (LIME, Counterfactuals, MC-LIME), across students from\\nthree diverse online courses. Our evaluation involves analyses of explanation\\nalignment to the social science theory, understandability of the explanation,\\nand a real-world user preference study with 114 university students containing\\na novel actionability simulation. We find that students prefer iLLuMinaTE\\nexplanations over traditional explainers 89.52% of the time. Our work provides\\na robust, ready-to-use framework for effectively communicating hybrid\\nXAI-driven insights in education, with significant generalization potential for\\nother human-centric fields.\",\"PeriodicalId\":501541,\"journal\":{\"name\":\"arXiv - CS - Human-Computer Interaction\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Human-Computer Interaction\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08027\",\"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 - Human-Computer Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08027","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

教育领域的可解释人工智能(XAI)的最新进展凸显了一个严峻的挑战:确保最先进的人工智能模型的解释能够为教育工作者和学生等非技术用户所理解。作为回应,我们介绍了 iLLuMinaTE,这是一个零射程、链式 LLM-XAI 管道,其灵感来自米勒的认知解释模型。iLLuMinaTE 设计用于向在线课程的学生提供理论驱动、可操作的反馈。iLLuMinaTE 通过三个主要阶段--因果联系、解释选择和解释呈现--从八种社会科学理论(如非正常情况、珀尔解释模型、必要性和稳健性选择、对比解释)中汲取变化。我们使用三种不同的基础 XAI 方法(LIME、Counterfactuals、MC-LIME),对来自三个不同在线课程的学生对 iLLuMinaTE 的 21,915 条自然语言解释进行了广泛评估,这些解释摘自三个 LLM(GPT-4o、Gemma2-9B、Llama3-70B)。我们的评估包括分析解释与社会科学理论的一致性、解释的可理解性,以及对 114 名大学生进行的真实世界用户偏好研究,其中包含一个新颖的可操作性模拟。我们发现,在 89.52% 的情况下,学生更喜欢 iLLuMinaTE 解释,而不是传统的解释。我们的工作为在教育领域有效传达混合 XAI 驱动的见解提供了一个强大的、随时可用的框架,并为其他以人为本的领域带来了巨大的推广潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
From Explanations to Action: A Zero-Shot, Theory-Driven LLM Framework for Student Performance Feedback
Recent advances in eXplainable AI (XAI) for education have highlighted a critical challenge: ensuring that explanations for state-of-the-art AI models are understandable for non-technical users such as educators and students. In response, we introduce iLLuMinaTE, a zero-shot, chain-of-prompts LLM-XAI pipeline inspired by Miller's cognitive model of explanation. iLLuMinaTE is designed to deliver theory-driven, actionable feedback to students in online courses. iLLuMinaTE navigates three main stages - causal connection, explanation selection, and explanation presentation - with variations drawing from eight social science theories (e.g. Abnormal Conditions, Pearl's Model of Explanation, Necessity and Robustness Selection, Contrastive Explanation). We extensively evaluate 21,915 natural language explanations of iLLuMinaTE extracted from three LLMs (GPT-4o, Gemma2-9B, Llama3-70B), with three different underlying XAI methods (LIME, Counterfactuals, MC-LIME), across students from three diverse online courses. Our evaluation involves analyses of explanation alignment to the social science theory, understandability of the explanation, and a real-world user preference study with 114 university students containing a novel actionability simulation. We find that students prefer iLLuMinaTE explanations over traditional explainers 89.52% of the time. Our work provides a robust, ready-to-use framework for effectively communicating hybrid XAI-driven insights in education, with significant generalization potential for other human-centric fields.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信