用语义ID解决对话新闻推荐中的隐式意图难题，实现零幻觉精准推荐。
Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation
- 基于生成-匹配范式，将用户意图映射为分层语义ID前缀。
- 在152K语义空间中实现12.4%的L1匹配率，零幻觉，成本仅为基线的1/100。
- 适用于冷启动用户，首次在零历史记录下实现18.0%的推荐准确率。
对话式新闻推荐需在快速变化的文章库中进行精准定位，同时处理缺乏显式关键词的隐式用户意图。我们从生产对话中识别出6类意图，其中5类为隐式，构成标准RAG流程的严重瓶颈。为此，提出在生成-匹配范式下的意图驱动语义ID（SID）生成方法。通过两阶段训练——多任务SID对齐与GPT-4思维链蒸馏，大模型将多样意图映射为层级化SID前缀，并通过模糊匹配当前新闻池，确保推荐完全可追溯。引入面向用户画像的双信号推理（PADR），使冷启动用户也能获得有效推荐。在主流中文新闻平台测试中，7B模型在152K开放生成的语义空间中实现0%幻觉和12.4% L1匹配率（4倍于随机基线），在L1上媲美GPT-4+混合RAG，且在更细粒度指标上表现更优（L2提升2倍，类别准确率+1.2个百分点），成本仅为后者的约1/100。冷启动用户（此前基线得分为0%）达到18.0% L1匹配率（6倍随机），在所有用户群体中最高。
原文摘要 · Abstract (English)
Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. To characterize this scenario, we identify 6 intent types from production dialogues: five are implicit and pose fundamental challenges to standard RAG pipelines, forming a critical retrieve-first bottleneck. To address these issues, we introduce intent-driven Semantic ID (SID) generation under a Generate-then-Match paradigm. With two-stage training that consists of multi-task SID alignment and GPT-4 Chain-of-Thought distillation, an LLM maps diverse intents to hierarchical SID prefixes, which are then fuzzy-matched to the current news pool to guarantee fully grounded recommendations. Profile-Aware Dual-Signal Reasoning (PADR) further enables cold-start users to obtain valid recommendations using only profiles. On a mainstream Chinese news platform, our 7B model achieves 0% hallucination and 12.4% L1 match in the 152K open-generation SID space (4x random baseline). It matches GPT-4+Hybrid RAG on L1 while surpassing it on finer-grained metrics (L2 2x, Category +1.2pp) at ~100x lower cost. Cold-start users, where existing baselines score 0%, achieve 18.0% L1 (6x random), the highest among all user groups.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。