While language models (LMs) offer great potential for conversational recommender systems (CRSs), the paucity of public CRS data makes fine-tuning LMs for CRSs challenging. In response, LMs as user simulators qua data generators can be used to train LM-based CRSs, but often lack behavioral consistency, generating utterance sequences inconsistent with those of any real user. To address this, we develop a methodology for generating natural dialogues that are consistent with a user's underlying state using behavior simulators together with LM-prompting. We illustrate our approach by generating a large, open-source CRS data set with both preference elicitation and example critiquing. Rater evaluation on some of these dialogues shows them to exhibit considerable consistency, factuality and naturalness.
@article{arxiv.2510.02331,
title = {Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)},
author = {Moonkyung Ryu and Chih-Wei Hsu and Yinlam Chow and Mohammad Ghavamzadeh and Craig Boutilier},
journal= {arXiv preprint arXiv:2510.02331},
year = {2025}
}