发表机构
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对程序性写作中示例反馈缺乏个性化的问题，提出RELEX系统，通过多步骤检索流水线（质量评分、BM25相似性匹配、个性化解释）为学习者提供定制示例，实验证明其能提升写作表现和用户体验。
AI 中文摘要
撰写高质量的程序性文本对许多学习者来说是一项具有挑战性的任务。虽然基于示例的学习作为一种反馈方法已显示出前景，但当所有学习者都收到相同的内容而未考虑其个人输入或先前知识时，就会出现局限性。因此，一些学习者难以理解或关联反馈，觉得反馈冗余且无帮助。为解决此问题，我们提出了RELEX，一个自适应学习系统，旨在通过个性化基于示例的学习来增强程序性写作。我们系统的核心是一个多步骤的示例检索流水线，该流水线根据每个学习者的独特输入，为其选择更高质量且上下文相关的示例。我们在烹饪食谱领域实例化了我们的系统。具体而言，我们利用一个微调的大型语言模型来预测学习者烹饪食谱的质量分数。利用该分数，我们从超过180,000个食谱的庞大数据库中检索质量更高的食谱。接下来，我们应用BM25实时选择语义上最相似的食谱。最后，我们利用领域知识和正则表达式，用个性化的教学解释来丰富所选示例食谱。我们在一个2×2的对照研究（个性化与个性化示例、反思性提示与无提示）中评估了RELEX，共有200名参与者。我们的结果表明，提供量身定制的示例有助于提高写作表现和用户体验。
英文摘要
Writing high-quality procedural texts is a challenging task for many learners. While example-based learning has shown promise as a feedback approach, a limitation arises when all learners receive the same content without considering their individual input or prior knowledge. Consequently, some learners struggle to grasp or relate to the feedback, finding it redundant and unhelpful. To address this issue, we present RELEX, an adaptive learning system designed to enhance procedural writing through personalized example-based learning. The core of our system is a multi-step example retrieval pipeline that selects a higher quality and contextually relevant example for each learner based on their unique input. We instantiate our system in the domain of cooking recipes. Specifically, we leverage a fine-tuned Large Language Model to predict the quality score of the learner's cooking recipe. Using this score, we retrieve recipes with higher quality from a vast database of over 180,000 recipes. Next, we apply BM25 to select the semantically most similar recipe in real-time. Finally, we use domain knowledge and regular expressions to enrich the selected example recipe with personalized instructional explanations. We evaluate RELEX in a 2 x 2 controlled study (personalized vs. non-personalized examples, reflective prompts vs. none) with 200 participants. Our results show that providing tailored examples contributes to better writing performance and user experience.
CommentsAccepted manuscript. Published version in the International Journal of Artificial Intelligence in Education (CC BY 4.0), DOI: 10.1007/s40593-024-00405-1
Journal refInternational Journal of Artificial Intelligence in Education, 35, 330-366 (2025)
DOI：10.1007/s40593-024-00405-1
