Metraipolis › archive › dc_830777fb2c2f
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation — arXiv:2609.00086
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00086
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:32:47.204Z
- SHA-256 of the archived text
eb04f304851ed0b508748eee824990286c08f833dd4302658433fc7a6721907a- Stable URL of this page
https://metraipolis.com/documento/dc_830777fb2c2f
How to cite
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation — arXiv:2609.00086 — arXiv (en), https://arxiv.org/abs/2609.00086 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_830777fb2c2f (Metraipolis archive dc_830777fb2c2f, sha256 eb04f304851ed0b508748eee824990286c08f833dd4302658433fc7a6721907a)
BibTeX
@misc{dc830777fb2c2f,
title = {Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation — arXiv:2609.00086},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00086},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_830777fb2c2f; sha256 eb04f304851ed0b508748eee824990286c08f833dd4302658433fc7a6721907a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00086. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used as rerankers in conversational recommender systems, yet measured gains depend strongly on the retrieval and inference protocol. On the ReDial conversational movie recommendation benchmark, we compare proprietary, open-weight, and fine-tuned LLM rerankers with collaborative-filtering and sequential baselines in a shared retrieve-then-rerank pipeline. We vary candidate-pool size, first-stage retriever, and decoding temperature. With a shared semantic top-250 candidate pool and strict candidate-aware scoring, the best proprietary reranker reaches NDCG@10 of 0.1497, compared with 0.0939 for the strongest non-LLM baseline. The same reranker reaches 0.2925 in zero-shot generation, showing that unconstrained scoring can yield a much larger apparent advantage than matched-pool evaluation. No evaluated open-weight LLM outperforms the tuned shallow autoencoder baseline under this protocol. For the strongest proprietary and open-weight rerankers, switching from semantic to collaborative-filtering candidates raises NDCG@10 by more than 50%, showing that measured reranker performance is highly sensitive to candidate generation. For the best proprietary reranker, raising temperature from 0 to 1.0 increases top-10 Jaccard distance from 0.0900 to 0.1240 while mean NDCG@10 changes negligibly, whereas weaker LLMs show larger degradation. These ReDial results support treating candidate generation, candidate-pool size, scoring policy, and decoding configuration as required reporting fields rather than implementation details. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00086 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.738Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).