Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
This work addresses the challenge of distribution shifts in RAG systems for specialized domains, offering an incremental improvement over existing methods.
The paper tackles the problem of suboptimal generalization in Retrieval-Augmented Generation (RAG) systems when adapting to specialized domains by proposing TTARAG, a test-time adaptation method that dynamically updates parameters during inference, achieving substantial performance improvements across six specialized domains.
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG systems to specialized domains, challenges arise from distribution shifts, resulting in suboptimal generalization performance. In this work, we propose TTARAG, a test-time adaptation method that dynamically updates the language model's parameters during inference to improve RAG system performance in specialized domains. Our method introduces a simple yet effective approach where the model learns to predict retrieved content, enabling automatic parameter adjustment to the target domain. Through extensive experiments across six specialized domains, we demonstrate that TTARAG achieves substantial performance improvements over baseline RAG systems. Code available at https://github.com/sunxin000/TTARAG.