Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models
We present our proposed system named Sherlock to UNLP 2024 Shared Task on Question Answering winning first place. We employ a mix of methods, from using automatically translated datasets to perform supervised fine-tuning and direct preference optimization on instruction-tuned models, to model weight merging and retrieval augmented generation. We present and motivate our chosen sequence of steps, as well as an ablation study to understand the effect of each additional step. The resulting model and code are made publicly available (download links provided in the paper).
Code (1)
Tasks
Question AnsweringRetrievalRetrieval-augmented GenerationSimilar Papers 제목 키워드 기반
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation Download PDF Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu Published: 20 Aug 2025, Retrieval augmented generation…
Question AnsweringAccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications
We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers a pipeline for development efficiency wi…
Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge
Multi-hop question answering is widely used to evaluate the reasoning capabilities of large language models (LLMs), as it requires integrating multiple pieces of supporting knowledge to arrive at a correct answer. While …
Multi-hop Question AnsweringScience Question AnsweringContinual PretrainingRetrieval Augmented Generation for Domain-specific Question Answering
Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand th…
Language ModelingLanguage ModellingLarge Language ModelQuestion Answering+2Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning
This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated…
ChunkingQuestion GenerationQuestion-GenerationRAG+3