Score: 0

Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3

Published: June 19, 2025 | arXiv ID: 2506.16037v1

By: Xinyue Huang , Ziqi Lin , Fang Sun and more

Potential Business Impact:

Answers hard questions from long texts better.

Business Areas:
Augmented Reality Hardware, Software

This paper presents a novel Retrieval-Augmented Generation (RAG) framework tailored for complex question answering tasks, addressing challenges in multi-hop reasoning and contextual understanding across lengthy documents. Built upon LLaMA 3, the framework integrates a dense retrieval module with advanced context fusion and multi-hop reasoning mechanisms, enabling more accurate and coherent response generation. A joint optimization strategy combining retrieval likelihood and generation cross-entropy improves the model's robustness and adaptability. Experimental results show that the proposed system outperforms existing retrieval-augmented and generative baselines, confirming its effectiveness in delivering precise, contextually grounded answers.

Country of Origin
🇺🇸 United States

Page Count
5 pages

Category
Computer Science:
Computation and Language