# Enhancing Retrieval Augmentation via Adversarial Collaboration

arXiv: https://arxiv.org/abs/2509.14750 · HTML: https://mlsanity.com/paper/2509.14750/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 23 of 23)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Query2doc: Query Expansion with Large Language Models](https://mlsanity.com/paper/2303.07678/) (2023)
- [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [System 2 Attention (is something you might need too)](https://mlsanity.com/paper/2311.11829/) (2023)
- [Thread of Thought Unraveling Chaotic Contexts](https://mlsanity.com/paper/2311.08734/) (2023)
- [SAIL: Search-Augmented Instruction Learning](https://mlsanity.com/paper/2305.15225/) (2023)

## Built on by (most cited first, 1 of 1)

- [FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic Hallucinations](https://mlsanity.com/paper/2512.07015/) (2025)

## Abstract (arXiv)

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.