Abstract

<title>Abstract</title> This paper presents a novel Retrieval-AugmentedGeneration (RAG) framework tailored for complex questionanswering tasks, addressing challenges in multi-hop reasoningand contextual understanding across lengthy documents. Builtupon LLaMA 3, the framework integrates a dense retrievalmodule with advanced context fusion and multi-hop reasoningmechanisms, enabling more accurate and coherent responsegeneration. A joint optimization strategy combining retrievallikelihood and generation cross-entropy improves the model’srobustness and adaptability. Experimental results show that theproposed system outperforms existing retrieval-augmented andgenerative baselines, confirming its effectiveness in deliveringprecise, contextually grounded answers.

Related Publications

Publication Info

Year
2025
Type
article
Citations
0
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

0
OpenAlex

Cite This

Xinyue Huang, Ziqi Lin, Fang Sun et al. (2025). Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3. . https://doi.org/10.21203/rs.3.rs-8296653/v1

Identifiers

DOI
10.21203/rs.3.rs-8296653/v1