How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval
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_ | 1866929432388698112 |
|---|---|
| author | Mo, Fengran Zhao, Longxiang Huang, Kaiyu Dong, Yue Huang, Degen Nie, Jian-Yun |
| author_facet | Mo, Fengran Zhao, Longxiang Huang, Kaiyu Dong, Yue Huang, Degen Nie, Jian-Yun |
| contents | Personalized conversational information retrieval (CIR) combines conversational and personalizable elements to satisfy various users' complex information needs through multi-turn interaction based on their backgrounds. The key promise is that the personal textual knowledge base (PTKB) can improve the CIR effectiveness because the retrieval results can be more related to the user's background. However, PTKB is noisy: not every piece of knowledge in PTKB is relevant to the specific query at hand. In this paper, we explore and test several ways to select knowledge from PTKB and use it for query reformulation by using a large language model (LLM). The experimental results show the PTKB might not always improve the search results when used alone, but LLM can help generate a more appropriate personalized query when high-quality guidance is provided. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval Mo, Fengran Zhao, Longxiang Huang, Kaiyu Dong, Yue Huang, Degen Nie, Jian-Yun Information Retrieval Computation and Language Personalized conversational information retrieval (CIR) combines conversational and personalizable elements to satisfy various users' complex information needs through multi-turn interaction based on their backgrounds. The key promise is that the personal textual knowledge base (PTKB) can improve the CIR effectiveness because the retrieval results can be more related to the user's background. However, PTKB is noisy: not every piece of knowledge in PTKB is relevant to the specific query at hand. In this paper, we explore and test several ways to select knowledge from PTKB and use it for query reformulation by using a large language model (LLM). The experimental results show the PTKB might not always improve the search results when used alone, but LLM can help generate a more appropriate personalized query when high-quality guidance is provided. |
| title | How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2407.16192 |