Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3
By: Xinyue Huang , Ziqi Lin , Fang Sun and more
Potential Business Impact:
Answers hard questions from long texts better.
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.
Similar Papers
Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
Computation and Language
Answers hard questions by breaking them down.
Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
Computation and Language
Helps AI answer harder questions faster.
Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning
Information Retrieval
Helps computers find answers by asking questions.