Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3
Authors:
- 16 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1339-1343
Abstract
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Tax Share Analysis and Prediction of Kernel Extreme Learning Machine Optimized by Vector Weighted Average AlgorithmAdvances in Economics, Management and Political Sciences, 2025
- Gemini-GraphQA: Integrating Language Models and Graph Encoders for Executable Graph ReasoningPreprints.org, 2025
- Towards Intelligent Cloud Scheduling: DynaSched-Net with Reinforcement Learning and Predictive ModelingPreprints.org, 2025
- Attention-Driven Interaction Network for E-Commerce RecommendationsPreprints.org, 2025
- Breast Cancer Risk Prediction: A Machine Learning Study Using Network Analysis2025
- CAB-KWS : Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology2024
- Coarse-to-Fine Multi-View 3D Reconstruction with SLAM Optimization and Transformer-Based Matching2024
- HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction2024
- Evaluating Retrieval-Augmented Generation Models for Financial Report Question and AnsweringApplied Sciences, 2024
- FinTextQA: A Dataset for Long-form Financial Question Answering2024