Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation

• URL: http://arxiv.org/abs/2603.18573v1
• Date: Thu, 19 Mar 2026 07:33:50 GMT
• Title: Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation
• Abstract summary: We propose a reference-free simulation framework that trains two independent large language models (LLMs)<n>These models interact in real-time without access to predetermined target items, but preference summaries and target attributes.<n>This approach produces more realistic and diverse conversations that closely mirror authentic human-AI interactions.
• Score: 29.520574514713402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training conversational recommender systems (CRS) requires extensive dialogue data, which is challenging to collect at scale. To address this, researchers have used simulated user-recommender conversations. Traditional simulation approaches often utilize a single large language model (LLM) that generates entire conversations with prior knowledge of the target items, leading to scripted and artificial dialogues. We propose a reference-free simulation framework that trains two independent LLMs, one as the user and one as the conversational recommender. These models interact in real-time without access to predetermined target items, but preference summaries and target attributes, enabling the recommender to genuinely infer user preferences through dialogue. This approach produces more realistic and diverse conversations that closely mirror authentic human-AI interactions. Our reference-free simulators match or exceed existing methods in quality, while offering a scalable solution for generating high-quality conversational recommendation data without constraining conversations to pre-defined target items. We conduct both quantitative and human evaluations to confirm the effectiveness of our reference-free approach.

Related papers

• VOGUE: A Multimodal Dataset for Conversational Recommendation in Fashion [18.017186369021154]
  VOGUE is a novel dataset of 60 humanhuman dialogues in realistic fashion shopping scenarios.<n>Each dialogue is paired with a shared visual catalogue, item metadata, user fashion profiles and histories, and post-conversation ratings from both Seekers and Assistants.<n>Our initial analyses of VOGUE reveal distinctive dynamics of visually grounded dialogue.
  arXiv  Detail & Related papers  (2025-10-24T04:45:29Z)
• STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation [18.833994388759326]
  We introduce STEP, a conversational recommender centered on pre-trained language models.<n> STEP combines curriculum-guided context-knowledge fusion with lightweight task-specific prompt tuning.<n> Experimental results show that STEP outperforms mainstream methods in the precision of recommendation and dialogue quality in two public datasets.
  arXiv  Detail & Related papers  (2025-08-14T14:08:21Z)
• 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)
• Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action [12.637812936971049]
  We present Conversational Sales (CSALES), a novel task that integrates preference elicitation, recommendation and persuasion within a unified conversational framework.<n>We also propose CSI, a conversational sales agent that proactively infers contextual user profiles and strategically selects actions through conversation.
  arXiv  Detail & Related papers  (2025-03-28T15:49:52Z)
• Identifying Breakdowns in Conversational Recommender Systems using User Simulation [15.54070473873364]
  We present a methodology to test conversational recommender systems with regards to conversational breakdowns. It involves examining conversations generated between the system and simulated users for a set of pre-defined breakdown types. We apply our methodology in a case study with an existing conversational recommender system and user simulator, demonstrating that with just a few iterations, we can make the system more robust to conversational breakdowns.
  arXiv  Detail & Related papers  (2024-05-23T07:28:26Z)
• Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems [2.788542465279969]
  This paper introduces DAUS, a Domain-Aware User Simulator. We fine-tune DAUS on real examples of task-oriented dialogues. Results on two relevant benchmarks showcase significant improvements in terms of user goal fulfillment.
  arXiv  Detail & Related papers  (2024-02-20T20:57:47Z)
• Parameter-Efficient Conversational Recommender System as a Language Processing Task [52.47087212618396]
  Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation. Prior work often utilizes external knowledge graphs for items' semantic information, a language model for dialogue generation, and a recommendation module for ranking relevant items. In this paper, we represent items in natural language and formulate CRS as a natural language processing task.
  arXiv  Detail & Related papers  (2024-01-25T14:07:34Z)
• 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)
• Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation [62.019437228000776]
  We present TalkWalk, which generates realistic high-quality conversational data by leveraging encoded expertise in widely available item collections. We generate over one million diverse conversations in a human-collected dataset.
  arXiv  Detail & Related papers  (2023-01-27T01:54:16Z)
• Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users [111.28351584726092]
  We consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively. Our Conversational Thompson Sampling (ConTS) model holistically solves all questions in conversational recommendation by choosing the arm with the maximal reward to play.
  arXiv  Detail & Related papers  (2020-05-23T08:56:37Z)

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.