Adaptive Personalized Conversational Information Retrieval

TL;DR

This paper introduces an adaptive personalization framework for conversational information retrieval that dynamically determines when and how to personalize search results, improving effectiveness over existing methods.

Contribution

The paper proposes a novel adaptive personalization approach that identifies the need for personalization per query and dynamically fuses reformulated queries for improved retrieval performance.

Findings

Outperforms state-of-the-art methods on TREC iKAT datasets.

Effectively identifies when personalization is needed for each query.

Enhances retrieval accuracy through dynamic query reformulation and fusion.

Abstract

Personalized conversational information retrieval (CIR) systems aim to satisfy users' complex information needs through multi-turn interactions by considering user profiles. However, not all search queries require personalization. The challenge lies in appropriately incorporating personalization elements into search when needed. Most existing studies implicitly incorporate users' personal information and conversational context using large language models without distinguishing the specific requirements for each query turn. Such a ``one-size-fits-all'' personalization strategy might lead to sub-optimal results. In this paper, we propose an adaptive personalization method, in which we first identify the required personalization level for a query and integrate personalized queries with other query reformulations to produce various enhanced queries. Then, we design a personalization-aware ranking fusion approach to assign fusion weights dynamically to different reformulated queries, depending on the required personalization level. The proposed adaptive personalized conversational information retrieval framework APCIR is evaluated on two TREC iKAT datasets. The results confirm the effectiveness of adaptive personalization of APCIR by outperforming state-of-the-art methods.