An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms

TL;DR

This paper introduces SynthRAG, an adaptive framework for generating systematic, comprehensive, and coherent explanatory answers in online Q&A platforms, significantly improving response quality for complex questions.

Contribution

SynthRAG is a novel framework that employs adaptive outlines and systematic thinking to enhance answer generation in QA systems, addressing limitations of naive RAG models.

Findings

SynthRAG outperforms naive RAG models in answer quality and depth.

Online deployment shows high user engagement and surpasses most human contributors.

Empirical results validate SynthRAG's effectiveness in complex question answering.

Abstract

Question Answering (QA) systems face challenges in handling complex questions that require multi-domain knowledge synthesis. The naive RAG models, although effective in information retrieval, struggle with complex questions that require comprehensive and in-depth answers. The pioneering task is defined as explanatory answer generation, which entails handling identified challenges such as the requirement for comprehensive information and logical coherence within the generated context. To address these issues, we refer to systematic thinking theory and propose SynthRAG, an innovative framework designed to enhance QA performance. SynthRAG improves on conventional models by employing adaptive outlines for dynamic content structuring, generating systematic information to ensure detailed coverage, and producing customized answers tailored to specific user inquiries. This structured approach guarantees logical coherence and thorough integration of information, yielding responses that are both insightful and methodically organized. Empirical evaluations underscore SynthRAG's effectiveness, demonstrating its superiority in handling complex questions, overcoming the limitations of naive RAG models, and significantly improving answer quality and depth. Furthermore, an online deployment on the Zhihu platform revealed that SynthRAG's answers achieved notable user engagement, with each response averaging 5.73 upvotes and surpassing the performance of 79.8% of human contributors, highlighting the practical relevance and impact of the proposed framework. Our code is available at https://github.com/czy1999/SynthRAG .