Adaptive meta-learning improves noise robustness in retrieval augmented generation
ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning
Artificial Intelligence
Summary
Retrieval-Augmented Generation (RAG) systems try to answer questions using external information, but sometimes the extra information contains mistakes or noise. The authors say that making RAG systems better at handling this noise involves three key skills: knowing when information might be wrong, checking the retrieved facts, and reasoning well despite errors. They created ARMOR, which uses a teaching-style method to help the system learn these skills step-by-step. Tests show ARMOR helps RAG systems give better answers even with noisy information.
What this means in practice
- •For natural language processing teams: Build more reliable question answering tools that maintain answer quality despite noisy external knowledge retrieval.
- •For customer support automation teams: Develop robust automated agents that can handle imperfect or noisy knowledge base entries when assisting users.
Authors
Yan Wang, Yuxin Zhang, Shenyu Zhang, Yongrui Chen, Sheng Bi, Guilin Qi
Abstract
Retrieval-Augmented Generation (RAG) systems have demonstrated remarkable effectiveness in mitigating hallucinations by incorporating external knowledge. However, the retrieval process inevitably introduces noise, posing significant challenges to RAG robustness. Fundamentally, noise robustness is a composite competency encompassing noise identification, retrieval filtering, and robust reasoning. Unfortunately, existing methods often fail to capture this holistic nature, typically restricted to single-dimensional enhancements or hampered by noise-induced optimization interference. To address these limitations, we decompose RAG robustness into three sub-tasks: knowledge boundary perception, retrieval verification, and robust reasoning. Accordingly, we propose ARMOR, an Adaptive Curriculum Meta-Learning for Noise Robust RAG Reasoning. Inspired by the teaching process, ARMOR introduces an adaptive task scheduler as a teacher to curate training plans according to the absolute learning progress of RAG generators (Student). Distinct from GRPO, ARMOR utilizes inter-group advantage estimation during learning to effectively mitigate mode collapse caused by limited output spaces. Experiments on three complex reasoning datasets (2WikiMultiHopQA, MusiQue, and HotPotQA) indicate that ARMOR achieves synergistic improvements in retrieval noise robustness, significantly outperforming baselines in output quality.