State of the Art of User Simulation approaches for conversational information retrieval

TL;DR

This paper reviews the current state of user simulation approaches in conversational information retrieval, emphasizing the importance of realistic user models for optimizing IR systems through reinforcement learning.

Contribution

It provides a comprehensive review of user modeling and simulation techniques in CIR and discusses future research directions in this area.

Findings

Reinforcement learning is promising for CIR but requires realistic user simulations.

Current literature on user modeling for IR is diverse and evolving.

Future research should focus on improving user simulation fidelity for better IR system training.

Abstract

Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information needs. In order to optimize these interactions and enhance the user experience, it is necessary to improve IR models by taking into account sequential heterogeneous user-system interactions. Reinforcement learning has emerged as a paradigm particularly suited to optimize sequential decision making in many domains and has recently appeared in IR. However, training these systems by reinforcement learning on users is not feasible. One solution is to train IR systems on user simulations that model the behavior of real users. Our contribution is twofold: 1)reviewing the literature on user modeling and user simulation for information access, and 2) discussing the different research perspectives for user simulations in the context of CIR