Enhancing Retrieval Augmentation via Adversarial Collaboration
This addresses retrieval hallucinations in domain-specific LLMs, offering a novel approach to enhance RAG performance.
The paper tackles the problem of retrieval hallucinations in retrieval-augmented generation (RAG) by proposing the AC-RAG framework, which uses adversarial collaboration between agents to improve retrieval accuracy and outperforms state-of-the-art methods across domains.
Retrieval-augmented Generation (RAG) is a prevalent approach for domain-specific LLMs, yet it is often plagued by "Retrieval Hallucinations"--a phenomenon where fine-tuned models fail to recognize and act upon poor-quality retrieved documents, thus undermining performance. To address this, we propose the Adversarial Collaboration RAG (AC-RAG) framework. AC-RAG employs two heterogeneous agents: a generalist Detector that identifies knowledge gaps, and a domain-specialized Resolver that provides precise solutions. Guided by a moderator, these agents engage in an adversarial collaboration, where the Detector's persistent questioning challenges the Resolver's expertise. This dynamic process allows for iterative problem dissection and refined knowledge retrieval. Extensive experiments show that AC-RAG significantly improves retrieval accuracy and outperforms state-of-the-art RAG methods across various vertical domains.