用强化推理提升UGC平台检索生成的相关性判断
R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
- 分两步判断相关性：先推断用户意图，再找原文证据片段
- 在离线测试中超越强基线，在线上测试中显著提升效果
- 适合需要高精度相关性评估的社交、内容平台
检索增强生成（RAG）在用户生成内容（UGC）平台中至关重要，但其效果高度依赖查询与文档的相关性判断。尽管大语言模型（LLMs）已用于相关性建模，但UGC平台面临两大挑战：1）由于RAG场景下用户反馈稀疏，用户意图模糊；2）相关性具有非对称性，由局部承载答案的内容驱动，而非全局相似度。为此，我们提出强化推理相关性评估模型R3A，将相关性判断分解为意图推断与证据定位两步。R3A利用高点击文档辅助推断隐含查询意图，并提取原文片段作为证据支撑判断，降低噪声敏感性，增强非对称相关性建模能力。实验表明，R3A在离线基准上显著优于强基线；其精简版R3A-1.5B模型在大规模线上A/B测试中实现显著性能提升，有效平衡了效果与部署可行性。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) plays a critical role in user-generated content (UGC) platforms, but its effectiveness critically depends on accurate query-document relevance assessment. Despite recent advances in applying large language models (LLMs) to relevance modeling, UGC platforms present unique challenges: 1) ambiguous user intent due to sparse user feedback in RAG scenarios, and 2) asymmetric relevance, where relevance is driven by localized answer-bearing content rather than global query-document similarity. To address these issues, we propose the Reinforced Reasoning model for Relevance Assessment (R3A), which decomposes relevance assessment into intent inference and evidence grounding. R3A leverages auxiliary high-clicked documents to infer latent query intent, and extracts verbatim evidence fragments to ground relevance decisions, reducing noise sensitivity and improving asymmetric relevance modeling. Experimental results demonstrate that R3A substantially outperforms strong baselines on offline benchmarks, while the distilled R3A-1.5B model achieves significant gains in large-scale online A/B testing, effectively balancing performance and practical deployability.
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。