发表机构
Naver; Samsung（纳弗公司; 三星公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
在ACM RecSys Challenge 2026中，团队“swyoo”将检索与响应解耦为单独管道，结合混合池与LightGBM校准候选，再经PAS框架构建响应，实现基于证据的对话式音乐推荐，在排名和解释质量上取得佳绩。
AI 中文摘要
传统对话式推荐器在单一文本界面中纠缠检索和响应生成，随着对话意图演变，确切实体线索消失，损害了解释可信度。我们在ACM RecSys Challenge 2026中解决此问题，该挑战要求前20排名和基于证据的响应生成。本文展示了团队“swyoo”在Blind-B行业赛道的季军解决方案。我们将检索和响应解耦为通过排名曲目和元数据严格连接的单独管道。检索结合混合词汇密集池进行精确匹配和由微调的Qwen 8B适配器驱动的任务适应池。候选通过LightGBM校准，然后路由到基于证据的提议-分配-选择（PAS）框架来构建响应。该系统在最终盲评的解释质量排行榜上也排名第二。我们的发现表明：（i）隔离检索和响应可保留目录线索和灵活意图；（ii）通过明确证据分配构建生成是实现近乎一流的解释可靠性的关键。
英文摘要
Traditional conversational recommenders entangle retrieval and response generation within a single text interface, so exact entity cues fade as the dialogue's intent evolves, which compromises explanation credibility. We address this within the ACM RecSys Challenge 2026, which mandates both top-20 ranking and evidence-grounded response generation. This paper presents the third-place solution by team "swyoo" for the Blind-B industry track. We decouple retrieval and response into separate pipelines connected strictly via ranked tracks and metadata. Retrieval combines a hybrid lexical-dense pool for exact matching with a task-adapted pool driven by fine-tuned Qwen 8B adapters. Candidates are calibrated via LightGBM, then routed to an evidence-grounded propose-assign-select (PAS) framework to structure responses. This system also ranked second on the explanation-quality leaderboard in the final blind evaluation. Our findings demonstrate that: (i) isolating retrieval and response preserves both catalog cues and fluid intent; (ii) structuring generation via explicit evidence assignment is key to this near-best-in-class explanation reliability.
Comments5 pages, 4 figures, 5 tables. 4th-place solution (team swyoo) in the Blind-B industry track of the ACM RecSys Challenge 2026
Journal refACM RecSys Challenge 2026
