Adaptive Personalized Conversational Information Retrieval
This work addresses the challenge of avoiding over-personalization in conversational search systems, which is an incremental improvement for users and developers of information retrieval technologies.
The paper tackles the problem of determining when to apply personalization in conversational information retrieval by proposing an adaptive method that identifies the required personalization level for each query and dynamically fuses reformulated queries, achieving state-of-the-art results on TREC iKAT datasets.
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.