Metraipolis › archive › dc_eefdf96e24ef

Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation — arXiv:2608.23484

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.23484
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:58.514Z
SHA-256 of the archived text: dfb38774fd05bc998600293cd2e138cd611d6926ea4a58354e9e87f1938fa71c
Stable URL of this page: https://metraipolis.com/documento/dc_eefdf96e24ef

How to cite

Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation — arXiv:2608.23484 — arXiv (en), https://arxiv.org/abs/2608.23484 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eefdf96e24ef (Metraipolis archive dc_eefdf96e24ef, sha256 dfb38774fd05bc998600293cd2e138cd611d6926ea4a58354e9e87f1938fa71c)

BibTeX

@misc{dceefdf96e24ef,
  title = {Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation — arXiv:2608.23484},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23484},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eefdf96e24ef; sha256 dfb38774fd05bc998600293cd2e138cd611d6926ea4a58354e9e87f1938fa71c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23484. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a multi-modal and personalized conversational recommender system. Our submitted system employs a three-stage pipeline: (1) multi-modal retrieval constructing decay-weighted centroids across seven dense embedding spaces - track- and user-level CF-BPR, Qwen3 (metadata, lyrics, attributes), CLAP audio, and SigLIP visual - supplemented by BM25 lexical retrieval and an artist substring-match signal, all fused via weighted Reciprocal Rank Fusion (RRF) with optimized signal weights; (2) lightweight reranking (history filtering, popularity smoothing, and catalog diversity penalization); and (3) persona-diversified response generation using GPT-4o-mini. Beyond this submitted configuration, we report development-time experiments with additional components - constrained LLM-guided artist injection, album continuation signals, XGBoost LambdaMART, and a superior GPT-4.1 response prompt - that were not deployed to Blind B due to cost and complexity constraints. We optimize RRF weights on a 500-session development split via differential evolution, improving MRR by +19.5%. On Blind A, we observe that unconstrained LLM-guided injection across 54 sessions causes catastrophic nDCG regression (-18.9%), while conservative injection on only 9 sessions yields the best observed Blind A nDCG - a finding we present as a Blind A observation warranting further validation. The submitted system achieves a Blind B composite score of 0.3213.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.23484 — 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 2026-10-18T07:37:52.781Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).