End-to-end Training for Recommendation with Language-based User Profiles
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929712508436480 |
|---|---|
| author | Gao, Zhaolin Zhou, Joyce Dai, Yijia Joachims, Thorsten |
| author_facet | Gao, Zhaolin Zhou, Joyce Dai, Yijia Joachims, Thorsten |
| contents | There is a growing interest in natural language-based user profiles for recommender systems, which aims to enhance transparency and scrutability compared with embedding-based methods. Existing studies primarily generate these profiles using zero-shot inference from large language models (LLMs), but their quality remains insufficient, leading to suboptimal recommendation performance. In this paper, we introduce LangPTune, the first end-to-end training framework to optimize LLM-generated user profiles. Our method significantly outperforms zero-shot approaches by explicitly training the LLM for the recommendation objective. Through extensive evaluations across diverse training configurations and benchmarks, we demonstrate that LangPTune not only surpasses zero-shot baselines but can also matches the performance of state-of-the-art embedding-based methods. Finally, we investigate whether the training procedure preserves the interpretability of these profiles compared to zero-shot inference through both GPT-4 simulations and crowdworker user studies. Implementation of LangPTune can be found at https://github.com/ZhaolinGao/LangPTune. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18870 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | End-to-end Training for Recommendation with Language-based User Profiles Gao, Zhaolin Zhou, Joyce Dai, Yijia Joachims, Thorsten Information Retrieval Machine Learning There is a growing interest in natural language-based user profiles for recommender systems, which aims to enhance transparency and scrutability compared with embedding-based methods. Existing studies primarily generate these profiles using zero-shot inference from large language models (LLMs), but their quality remains insufficient, leading to suboptimal recommendation performance. In this paper, we introduce LangPTune, the first end-to-end training framework to optimize LLM-generated user profiles. Our method significantly outperforms zero-shot approaches by explicitly training the LLM for the recommendation objective. Through extensive evaluations across diverse training configurations and benchmarks, we demonstrate that LangPTune not only surpasses zero-shot baselines but can also matches the performance of state-of-the-art embedding-based methods. Finally, we investigate whether the training procedure preserves the interpretability of these profiles compared to zero-shot inference through both GPT-4 simulations and crowdworker user studies. Implementation of LangPTune can be found at https://github.com/ZhaolinGao/LangPTune. |
| title | End-to-end Training for Recommendation with Language-based User Profiles |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2410.18870 |