Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation
Read the original on arXiv AI →The study evaluates large language models (LLMs) as rerankers in conversational movie recommendation, comparing proprietary, open-weight, and fine-tuned LLMs against collaborative-filtering and sequential baselines on the ReDial benchmark. Results show that the best proprietary LLM achieves an NDCG@10 of 0.1497 with a shared semantic candidate pool, outperforming non-LLM baselines, while open-weight LLMs do not surpass a tuned shallow autoencoder under the same protocol. The analysis also highlights that reranker performance is highly sensitive to candidate generation, pool size, scoring policy, and decoding temperature, suggesting these factors should be reported as standard evaluation fields.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.