Can I read Aligning Language Models for Versatile Text-based Item Retrieval on EtoBox?

Aligning Language Models for Versatile Text-based Item Retrieval by Lei, Yuxuan; Lian, Jianxun; Yao, Jing; Wu, Mingqi; Lian, Defu; Xie, Xing is a scholarly article available to read on EtoBox.

What is Aligning Language Models for Versatile Text-based Item Retrieval about?

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.

Author

Lei, Yuxuan; Lian, Jianxun; Yao, Jing; Wu, Mingqi; Lian, Defu; Xie, Xing

Published

2024

Language

EN