OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning

📅 2025-03-11
📈 Citations: 0
Influential: 0
📄 PDF

career value

190K/year
🤖 AI Summary
To address the semantic relevance modeling mismatch between traditional retrievers and generators in retrieval-augmented generation (RAG), this paper proposes the first end-to-end differentiable retriever joint optimization framework. It enables collaborative training of retriever and generator via gradient backpropagation and introduces context-aware relevance modeling, allowing the retriever to explicitly learn task-specific semantic matching required by the generator. This approach is the first to support full-pipeline differentiability and dynamic task adaptation in RAG. Experiments demonstrate an average 4.0% improvement over baselines across multiple tasks and consistent superiority—by 2.1%—over state-of-the-art retrievers. Notably, a lightweight 0.2B-parameter retriever outperforms an 8B-parameter instruction-tuned LLM-enhanced RAG system on several tasks, achieving significant gains in both efficiency and performance trade-offs.

Technology Category

Application Category

📝 Abstract
In this paper, we analyze and empirically show that the learned relevance for conventional information retrieval (IR) scenarios may be inconsistent in retrieval-augmented generation (RAG) scenarios. To bridge this gap, we introduce OpenRAG, a RAG framework that is optimized end-to-end by tuning the retriever to capture in-context relevance, enabling adaptation to the diverse and evolving needs. Extensive experiments across a wide range of tasks demonstrate that OpenRAG, by tuning a retriever end-to-end, leads to a consistent improvement of 4.0% over the original retriever, consistently outperforming existing state-of-the-art retrievers by 2.1%. Additionally, our results indicate that for some tasks, an end-to-end tuned 0.2B retriever can achieve improvements that surpass those of RAG-oriented or instruction-tuned 8B large language models (LLMs), highlighting the cost-effectiveness of our approach in enhancing RAG systems.
Problem

Research questions and friction points this paper is trying to address.

Inconsistent relevance in RAG scenarios.
Optimizing retriever for in-context relevance.
Cost-effective improvement over large language models.
Innovation

Methods, ideas, or system contributions that make the work stand out.

End-to-end tuning of retriever for RAG optimization
In-context relevance learning for diverse task adaptation
Cost-effective retriever outperforms larger language models