Tag
This paper evaluates LLM rerankers in conversational recommendation systems, demonstrating that performance and stability are highly dependent on retrieval protocols, candidate pool configuration, and decoding settings.
This paper presents an empirical study on bootstrapping conversational recommender systems using synthetic data generated from non-conversational signals, demonstrating that it outperforms zero-shot and scarce real-data methods in low-resource settings.
This paper proposes a framework to automatically optimize prompts for LLM-based user simulators in conversational recommender systems, addressing issues like positive bias and limited behavioral diversity.