Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3
Preprint
- 19 June 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
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.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation2025
- Towards Intelligent Cloud Scheduling: DynaSched-Net with Reinforcement Learning and Predictive Modeling2025
- PrivacyPreserveNet: A Multilevel Privacy-Preserving Framework for Multimodal LLMs via Gradient Clipping and Attention Noise2025
- Attention-Driven Interaction Network for E-Commerce Recommendations2025
- FinTextQA: A Dataset for Long-form Financial Question Answering2024