Oct 2026· Proceedings of the Workshop on the ACM RecSys Challenge· 1 citation· ⚡ 1 influential· 3 references
TL;DR
Team npatta01’s submission to the RecSys Challenge 2026 conversational music recommendation task is described and failure cases from the submitted run show extracted constraints the pipeline could not enforce.
Abstract
We describe team npatta01’s submission to the RecSys Challenge 2026 conversational music recommendation task. The pipeline extracts a typed conversation state with an LLM, gathers candidates from eleven retrieval branches over a unified track index, re-ranks them with a LambdaMART model, and uses the state to generate a response. On the final Blind-B leaderboard it scored 0.3811 composite (nDCG@20 0.2537, LLM-judge 3.30), ranking 29th of 40 teams. We then examine why. The development estimates we selected on were computed in-sample and overstated performance. The training conversations are LLM-generated, and on many turns we were unsure that the single ground-truth track matched the request — often it repeats the just-played artist after an explicit request for someone else. We re-judged the turns with LLM judges and release that relabeling; a model trained on it scored lower against the original labels, so the submission kept them. Failure cases from the submitted run show extracted constraints the pipeline could not enforce. Code, models, and a full reproduction bundle are publicly released.
This diagnostic compares the full pipeline with reciprocal-rank fusion, ablate per-retriever features, and decompose ranking error into retrieval misses, reranking exclusions, and ranks-2–20 ordering loss and complement the leaderboard result with a diagnostic that fits on Train and evaluates the official Devset.
Ryohei Wakatsuki· Proceedings of the Workshop...· 1 citation
The RecSys Challenge 2026 studies conversational music recommendation as a joint item recommendation and response generation problem: given a multi-turn dialogue, systems must retrieve relevant tracks from a large catalog and produce a grounded natural-language response. This paper presents the challenge task, dataset,...
Seungheon Doh, Sergio Oramas, B. Sguerra et al.· Proceedings of the Workshop...· 0 citations
We present suryaaseran1, our conversational music recommender for the TalkPlayData Challenge (ACM RecSys 2026) that treats each dialogue turn’s user reactions as a preference-elicitation signal for both retrieval and ranking. The dataset’s goal-progress feedback is delayed by one turn and includes rejected tracks logge...
Suryaa Veerabathiran Seran· Proceedings of the Workshop...· 1 citation· ⚡1
The RecSys Challenge 2026 Music-CRS (TalkPlay) task formalizes this as two coupled sub-problems: given dialogue history and user context, retrieve a ranked list of the top-20 tracks from the full, unrestricted catalog, and generate a response that justifies the recommendation while sustaining conversational coherence.
Simran Sundrani, Mohan Bhambhani· Proceedings of the Workshop...· 1 citation· ⚡1
This paper describes the solution submitted by team Hallucinated to the ACM RecSys Challenge 2026, based on the TalkPlayData conversational music recommendation dataset. The Challenge poses a dual task: at every turn of a multi-turn dialogue, a system must both (i) rank the most relevant music tracks from the catalogue...
Abdallah Alkhetiar, Luigi Inguaggiato, Nicolò Locatelli et al.· Proceedings of the Workshop...· 1 citation
We describe a solo entry to the ACM RecSys Challenge 2026 Music-CRS track (team Siwon, CodaBench swlee9087): a frozen, inference-only system that combines BM25, a frozen instruction-tuned text embedder, and a listening-history centroid through Reciprocal Rank Fusion, followed by a two-stage response generator. It reach...
Siwon Lee, Young-June Choi· Proceedings of the Workshop...· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
