Enhancing Retrieval Augmentation via Adversarial Collaboration
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908773873876992 |
|---|---|
| author | Zhang, Letian Meng, Guanghao Ren, Xudong Wang, Yiming Xia, Shu-Tao |
| author_facet | Zhang, Letian Meng, Guanghao Ren, Xudong Wang, Yiming Xia, Shu-Tao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14750 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Retrieval Augmentation via Adversarial Collaboration Zhang, Letian Meng, Guanghao Ren, Xudong Wang, Yiming Xia, Shu-Tao Artificial Intelligence 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. |
| title | Enhancing Retrieval Augmentation via Adversarial Collaboration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.14750 |