REFINE On Scarce Data: Retrieval Enhancement Through Fine-tuning Via Model Fusion Of Embedding Models

Abstract

Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved context is inaccurate, the answers generated using the large language model (LLM) may contain errors or hallucinations. Although pretrained embedding models have advanced, adapting them to new domains remains challenging. Fine-tuning is a potential solution, but industry settings often lack the necessary fine-tuning data. To address these challenges, we propose REFINE, a novel technique that generates synthetic data from available documents and then uses a model fusion approach to fine-tune embeddings for improved retrieval performance in new domains, while preserving out-of-domain capability. We conducted experiments on the two public datasets: SQUAD and RAG-12000 and a proprietary TOURISM dataset. Results demonstrate that even the standard fine-tuni

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keygupta2024refine

Related papers

• Mafin: Enhancing Black-box Embeddings With Model Augmented Fine-tuning (2024)0.00
• Re-ranking The Context For Multimodal Retrieval Augmented Generation (2025)0.00
• Optimizing Retrieval For RAG Via Reinforcement Learning (2025)0.00
• Funnelrag: A Coarse-to-fine Progressive Retrieval Paradigm For RAG (2024)3.58
• Optimizing Retrieval-augmented Generation: Analysis Of Hyperparameter Impact On Performance And Efficiency (2025)0.00
• LMAR: Language Model Augmented Retriever For Domain-specific Knowledge Indexing (2025)1.57
• Advancing Retrieval-augmented Generation For Structured Enterprise And Internal Data (2025)1.20
• A Fine-tuning Enhanced RAG System With Quantized Influence Measure As AI Judge (2024)11.19