Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework

• URL: http://arxiv.org/abs/2607.00010v1
• Date: Fri, 08 May 2026 07:19:27 GMT
• Title: Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework
• Abstract summary: Conversational recommender systems (CRSs) enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time.<n> evaluating CRSs through real human studies is more critical than for traditional recommender systems.<n>CRS interaction data are often difficult to obtain for model training due to privacy concerns.<n>Existing approaches suffer from systematic positive bias, data leakage, and limited behavioral diversity.
• Score: 8.412921699661348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time. However, there are two key obstacles in the CRS domain: evaluation and access to training data. Evaluating CRSs through real human studies is more critical than for traditional recommender systems, yet such studies are both costly and time-consuming. Moreover, CRS interaction data are often difficult to obtain for model training due to privacy concerns. Large language model (LLM)-based user simulators have shown promise in addressing both challenges by generating synthetic user interactions for evaluation and training. However, existing approaches suffer from systematic positive bias, data leakage, and limited behavioral diversity, and they rely on brittle manual prompt engineering that requires extensive domain expertise. In this paper, we propose a framework to automatically optimize prompts for LLM-based user simulators in CRSs, simultaneously mitigating these issues. Experimental results demonstrate that the proposed framework achieves improved behavioral alignment with human interaction patterns compared to baseline methods across diverse prompt settings.

Related papers

• Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems [49.766845975588275]
  We propose a set of design desiderata and research questions to guide the development of a more realistic benchmark for unlearning in recommender systems.<n>We argue for an unlearning setup that reflects the sequential, time-sensitive nature of real-world deletion requests.<n>We present a preliminary experiment in a next-basket recommendation setting based on our proposed desiderata and find that unlearning also works for sequential recommendation models.
  arXiv  Detail & Related papers  (2025-08-23T16:05:40Z)
• Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation [18.01518720663732]
  Conversational recommender systems (CRSs) enhance recommendation quality by engaging users in multi-turn dialogues.<n>CRSs often face the false negative issue, where items that a user might like are incorrectly labeled as negative during training, leading to suboptimal recommendations.<n>We propose a novel data augmentation framework that first leverages an LLM-based semantic retriever to identify diverse and semantically relevant items.
  arXiv  Detail & Related papers  (2025-07-30T08:20:54Z)
• Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User [117.82681846559909]
  Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations.<n>We propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs.
  arXiv  Detail & Related papers  (2025-04-29T06:37:30Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems [21.275452863162936]
  PEPPER is an evaluation protocol with target-free user simulators constructed from real-user interaction histories and reviews.<n> PEPPER enables realistic user-CRS dialogues without falling into simplistic guessing games.<n> PEPPER presents detailed measures for comprehensively evaluating the preference elicitation capabilities of CRSs.
  arXiv  Detail & Related papers  (2024-11-25T07:36:20Z)
• Reformulating Conversational Recommender Systems as Tri-Phase Offline Policy Learning [5.453444582931813]
  Tri-Phase Offline Policy Learning-based Conversational Recommender System (TCRS) This paper introduces the Tri-Phase Offline Policy Learning-based Conversational Recommender System (TCRS)
  arXiv  Detail & Related papers  (2024-08-13T10:58:29Z)
• Improving Conversational Recommendation Systems via Counterfactual Data Simulation [73.4526400381668]
  Conversational recommender systems (CRSs) aim to provide recommendation services via natural language conversations. Existing CRS approaches often suffer from the issue of insufficient training due to the scarcity of training data. We propose a CounterFactual data simulation approach for CRS, named CFCRS, to alleviate the issue of data scarcity in CRSs.
  arXiv  Detail & Related papers  (2023-06-05T12:48:56Z)
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models [115.7508325840751]
  The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs) In this paper, we embark on an investigation into the utilization of ChatGPT for conversational recommendation, revealing the inadequacy of the existing evaluation protocol. We propose an interactive Evaluation approach based on LLMs named iEvaLM that harnesses LLM-based user simulators.
  arXiv  Detail & Related papers  (2023-05-22T15:12:43Z)
• Leveraging Historical Interaction Data for Improving Conversational Recommender System [105.90963882850265]
  We propose a novel pre-training approach to integrate item- and attribute-based preference sequence. Experiment results on two real-world datasets have demonstrated the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-08-19T03:43:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.