Aligning Language Models for Versatile Text-based Item Retrieval

Autor:	Lei, Yuxuan, Lian, Jianxun, Yao, Jing, Wu, Mingqi, Lian, Defu, Xie, Xing
Rok vydání:	2024
Předmět:	Computer Science - Information Retrieval
Druh dokumentu:	Working Paper
Popis:	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. Comment: 4 pages,1 figures, 4 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.18899 Zobrazit plný text záznamu View this record from Arxiv