Predict the Retrieval! Test Time Adaptation for Retrieval Augmented Generation

ACL ARR 2025 February Submission5762 Authors

Abstract: 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 \ourmethod achieves substantial performance improvements over baseline RAG systems.

Paper Type: Short

Research Area: Information Retrieval and Text Mining

Research Area Keywords: retrieval-augmented Generation

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5762