TREC iKAT 2023: The Interactive Knowledge Assistance Track Overview
It addresses the challenge of personalized conversational information seeking for users, but is incremental as it builds on existing LLM-based approaches.
The paper introduces the TREC iKAT 2023 track, which focuses on developing conversational search agents that personalize responses based on user interactions and context, with seven teams submitting 24 runs, primarily using Large Language Models.
Conversational Information Seeking has evolved rapidly in the last few years with the development of Large Language Models providing the basis for interpreting and responding in a naturalistic manner to user requests. iKAT emphasizes the creation and research of conversational search agents that adapt responses based on the user's prior interactions and present context. This means that the same question might yield varied answers, contingent on the user's profile and preferences. The challenge lies in enabling Conversational Search Agents (CSA) to incorporate personalized context to effectively guide users through the relevant information to them. iKAT's first year attracted seven teams and a total of 24 runs. Most of the runs leveraged Large Language Models (LLMs) in their pipelines, with a few focusing on a generate-then-retrieve approach.