Decomposed Reasoning with Reinforcement Learning for Relevance Assessment in UGC Platforms
By: Xiaowei Yuan , Lei Jin , Haoxin Zhang and more
Potential Business Impact:
Helps computers understand messy online posts better.
Retrieval-augmented generation (RAG) plays a critical role in user-generated content (UGC) platforms, but its effectiveness depends heavily on accurate relevance assessment of query-document pairs. 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) substantial noise introduced by informal and unstructured language. To address these issues, we propose the Reinforced Reasoning Model for Relevance Assessment (R3A), which introduces a decomposed reasoning framework over queries and candidate documents before scoring. R3A first leverages auxiliary high-ranked documents within the platform to infer latent query intent. It then performs verbatim fragment extraction to justify relevance decisions, thereby reducing errors caused by noisy UGC. Based on a reinforcement learning framework, R3A is optimized to mitigate distortions arising from ambiguous queries and unstructured content. Experimental results show that R3A significantly outperforms existing baseline methods in terms of relevance accuracy, across both offline benchmarks and online experiments.
Similar Papers
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Computation and Language
AI learns to find better answers by thinking.
Optimizing Retrieval for RAG via Reinforced Contrastive Learning
Computation and Language
AI learns to find better information for itself.
LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
Computation and Language
Makes smart computers answer questions faster and better.