Aligning Language Models for Versatile Text-based Item Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909123276177408 |
|---|---|
| author | Lei, Yuxuan Lian, Jianxun Yao, Jing Wu, Mingqi Lian, Defu Xie, Xing |
| author_facet | Lei, Yuxuan Lian, Jianxun Yao, Jing Wu, Mingqi Lian, Defu Xie, Xing |
| contents | This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item retrieval tasks. To overcome these limitations, we propose generate in-domain dataset from ten tasks tailored to unlocking models' representation ability for item retrieval. Our empirical studies demonstrate that fine-tuning embedding models on the dataset leads to remarkable improvements in a variety of retrieval tasks. We also illustrate the practical application of our refined model in a conversational setting, where it enhances the capabilities of LLM-based Recommender Agents like Chat-Rec. Our code is available at https://github.com/microsoft/RecAI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18899 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Language Models for Versatile Text-based Item Retrieval Lei, Yuxuan Lian, Jianxun Yao, Jing Wu, Mingqi Lian, Defu Xie, Xing Information Retrieval This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item retrieval tasks. To overcome these limitations, we propose generate in-domain dataset from ten tasks tailored to unlocking models' representation ability for item retrieval. Our empirical studies demonstrate that fine-tuning embedding models on the dataset leads to remarkable improvements in a variety of retrieval tasks. We also illustrate the practical application of our refined model in a conversational setting, where it enhances the capabilities of LLM-based Recommender Agents like Chat-Rec. Our code is available at https://github.com/microsoft/RecAI. |
| title | Aligning Language Models for Versatile Text-based Item Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2402.18899 |