How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval

TL;DR

This paper investigates leveraging personal textual knowledge bases for personalized conversational information retrieval, demonstrating how large language models can improve query reformulation despite PTKB noise.

Contribution

It explores methods to select and utilize PTKB for query reformulation using LLMs, highlighting the importance of high-quality guidance for effective personalization.

Findings

PTKB alone may not always improve retrieval results

LLMs can generate better personalized queries with proper guidance

Knowledge selection impacts retrieval effectiveness

Abstract

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.