Score: 1

Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation

Published: January 16, 2026 | arXiv ID: 2601.11443v1

By: Xin Sun , Zhongqi Chen , Qiang Liu and more

Potential Business Impact:

Helps AI answer questions better in new subjects.

Business Areas:
Augmented Reality Hardware, Software

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.

Country of Origin
šŸ‡ØšŸ‡³ China

Repos / Data Links

Page Count
5 pages

Category
Computer Science:
Computation and Language