Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

Mejia-Domenzain, Paola; Frej, Jibril; Neshaei, Seyed Parsa; Mouchel, Luca; Nazaretsky, Tanya; Wambsganss, Thiemo; Bosselut, Antoine; Käser, Tanja (2024). Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes International Journal of Artificial Intelligence in Education, pp. 1-37. Springer 10.1007/s40593-024-00405-1

Preview

Text s40593-024-00405-1.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (1MB) | Preview

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 2x2 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.

Item Type:	Journal Article (Original Article)
Division/Institute:	Business School > Institute for Digital Technology Management Business School
Name:	Mejia-Domenzain, Paola; Frej, Jibril; Neshaei, Seyed Parsa; Mouchel, Luca; Nazaretsky, Tanya; Wambsganss, Thiemo0000-0002-7440-9357; Bosselut, Antoine and Käser, Tanja
Subjects:	L Education > L Education (General) T Technology > T Technology (General)
ISSN:	1560-4292
Publisher:	Springer
Language:	English
Submitter:	Prof. Dr. Thiemo Wambsganss
Date Deposited:	13 Aug 2024 14:49
Last Modified:	13 Aug 2024 14:49
Publisher DOI:	10.1007/s40593-024-00405-1
Uncontrolled Keywords:	Example-based learning · Procedural writing · Large language models · Text quality evaluation
ARBOR DOI:	10.24451/arbor.22095
URI:	https://arbor.bfh.ch/id/eprint/22095