Search papers, labs, and topics across Lattice.
This paper introduces a reference-free simulation framework, Interplay, for training conversational recommender systems (CRS) by using two independently trained LLMs as user and recommender agents. Unlike existing methods that rely on pre-defined target items, Interplay allows the recommender to infer user preferences through real-time dialogue based on preference summaries and target attributes. Experiments demonstrate that Interplay generates more realistic and diverse conversations, matching or exceeding existing methods in quality while offering a scalable solution for data generation.
Escape the scripted feel of simulated conversations: Interplay trains independent user and recommender LLMs that interact in real-time, without pre-defined target items, for more realistic and diverse conversational recommendation data.
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.