Evaluating Conversational Recommender Systems via User Simulation
arXiv:2006.08732 · doi:10.1145/3394486.3403202
Abstract
Conversational information access is an emerging research area. Currently, human evaluation is used for end-to-end system evaluation, which is both very time and resource intensive at scale, and thus becomes a bottleneck of progress. As an alternative, we propose automated evaluation by means of simulating users. Our user simulator aims to generate responses that a real human would give by considering both individual preferences and the general flow of interaction with the system. We evaluate our simulation approach on an item recommendation task by comparing three existing conversational recommender systems. We show that preference modeling and task-specific interaction models both contribute to more realistic simulations, and can help achieve high correlation between automatic evaluation measures and manual human assessments.
Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '20), 2020
References in corpus (4)
Cited by in corpus (22)
- KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
- KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
- Evaluating Mixed-initiative Conversational Search Systems via User Simulation
- Evaluating Conversational Recommender Systems: A Landscape of Research
- Exploiting Simulated User Feedback for Conversational Search: Ranking, Rewriting, and Beyond
- Analysing Mixed Initiatives and Search Strategies during Conversational Search
- UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems
- Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems
- The Effects of System Initiative during Conversational Collaborative Search
- Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
- Alleviating the Long-Tail Problem in Conversational Recommender Systems
- Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems
- State Encoders in Reinforcement Learning for Recommendation: A Reproducibility Study
- RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
- Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access
- Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
- Identifying Breakdowns in Conversational Recommender Systems using User Simulation
- Leveraging User Simulation to Develop and Evaluate Conversational Information Access Agents
- DAGFiNN: A Conversational Conference Assistant
- EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context
- Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation
- IAI MovieBot 2.0: An Enhanced Research Platform with Trainable Neural Components and Transparent User Modeling