Ramos, J., Rahmani, H.A., Wang, X. orcid.org/0000-0001-5936-9919 et al. (2 more authors) (2024) Transparent and scrutable recommendations using natural language user profiles. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 62nd Annual Meeting of the Association for Computational Linguistics, 11-16 Aug 2024, Bangkok, Thailand. Association for Computational Linguistics , pp. 13971-13984.
Abstract
Recent state-of-the-art recommender systems predominantly rely on either implicit or explicit feedback from users to suggest new items. While effective in recommending novel options, many recommender systems often use uninterpretable embeddings to represent user preferences. This lack of transparency not only limits user understanding of why certain items are suggested but also reduces the user's ability to scrutinize and modify their preferences, thereby affecting their ability to receive a list of preferred recommendations. Given the recent advances in Large Language Models (LLMs), we investigate how a properly crafted prompt can be used to summarize a user's preferences from past reviews and recommend items based only on language-based preferences. In particular, we study how LLMs can be prompted to generate a natural language (NL) user profile that holistically describe a user's preferences. These NL profiles can then be leveraged to fine-tune a LLM using only NL profiles to make transparent and scrutable recommendations. Furthermore, we validate the scrutability of our user profile-based recommender by investigating the impact on recommendation changes after editing NL user profiles. According to our evaluations of the model's rating prediction performance on two benchmarking rating prediction datasets, we observe that this novel approach maintains a performance level on par with established recommender systems in a warm-start setting. With a systematic analysis into the effect of updating user profiles and system prompts, we show the advantage of our approach in easier adjustment of user preferences and a greater autonomy over users' received recommendations.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 Association for Computational Linguistics. Licensed on a Creative Commons Attribution 4.0 International License. (https://creativecommons.org/licenses/by/4.0/) |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Jan 2025 17:33 |
Last Modified: | 16 Jan 2025 15:16 |
Published Version: | https://aclanthology.org/2024.acl-long.753/ |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/2024.acl-long.753 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:221502 |