TEARS: Textual Representations for Scrutable Recommendations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916641761132544 |
|---|---|
| author | Penaloza, Emiliano Gouvert, Olivier Wu, Haolun Charlin, Laurent |
| author_facet | Penaloza, Emiliano Gouvert, Olivier Wu, Haolun Charlin, Laurent |
| contents | Traditional recommender systems rely on high-dimensional (latent) embeddings for modeling user-item interactions, often resulting in opaque representations that lack interpretability. Moreover, these systems offer limited control to users over their recommendations. Inspired by recent work, we introduce TExtuAl Representations for Scrutable recommendations (TEARS) to address these challenges. Instead of representing a user's interests through a latent embedding, TEARS encodes them in natural text, providing transparency and allowing users to edit them. To do so, TEARS uses a modern LLM to generate user summaries based on user preferences. We find the summaries capture user preferences uniquely. Using these summaries, we take a hybrid approach where we use an optimal transport procedure to align the summaries' representation with the learned representation of a standard VAE for collaborative filtering. We find this approach can surpass the performance of three popular VAE models while providing user-controllable recommendations. We also analyze the controllability of TEARS through three simulated user tasks to evaluate the effectiveness of a user editing its summary. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_19302 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TEARS: Textual Representations for Scrutable Recommendations Penaloza, Emiliano Gouvert, Olivier Wu, Haolun Charlin, Laurent Information Retrieval Artificial Intelligence Machine Learning Traditional recommender systems rely on high-dimensional (latent) embeddings for modeling user-item interactions, often resulting in opaque representations that lack interpretability. Moreover, these systems offer limited control to users over their recommendations. Inspired by recent work, we introduce TExtuAl Representations for Scrutable recommendations (TEARS) to address these challenges. Instead of representing a user's interests through a latent embedding, TEARS encodes them in natural text, providing transparency and allowing users to edit them. To do so, TEARS uses a modern LLM to generate user summaries based on user preferences. We find the summaries capture user preferences uniquely. Using these summaries, we take a hybrid approach where we use an optimal transport procedure to align the summaries' representation with the learned representation of a standard VAE for collaborative filtering. We find this approach can surpass the performance of three popular VAE models while providing user-controllable recommendations. We also analyze the controllability of TEARS through three simulated user tasks to evaluate the effectiveness of a user editing its summary. |
| title | TEARS: Textual Representations for Scrutable Recommendations |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.19302 |