Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.07307 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912585275670528 |
|---|---|
| author | Anik, Anirban Saha Song, Xiaoying Wang, Elliott Wang, Bryan Yarimbas, Bengisu Hong, Lingzi |
| author_facet | Anik, Anirban Saha Song, Xiaoying Wang, Elliott Wang, Bryan Yarimbas, Bengisu Hong, Lingzi |
| contents | Large language models (LLMs) incorporated with Retrieval-Augmented Generation (RAG) have demonstrated powerful capabilities in generating counterspeech against misinformation. However, current studies rely on limited evidence and offer less control over final outputs. To address these challenges, we propose a Multi-agent Retrieval-Augmented Framework to generate counterspeech against health misinformation, incorporating multiple LLMs to optimize knowledge retrieval, evidence enhancement, and response refinement. Our approach integrates both static and dynamic evidence, ensuring that the generated counterspeech is relevant, well-grounded, and up-to-date. Our method outperforms baseline approaches in politeness, relevance, informativeness, and factual accuracy, demonstrating its effectiveness in generating high-quality counterspeech. To further validate our approach, we conduct ablation studies to verify the necessity of each component in our framework. Furthermore, cross evaluations show that our system generalizes well across diverse health misinformation topics and datasets. And human evaluations reveal that refinement significantly enhances counterspeech quality and obtains human preference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation Anik, Anirban Saha Song, Xiaoying Wang, Elliott Wang, Bryan Yarimbas, Bengisu Hong, Lingzi Computation and Language Large language models (LLMs) incorporated with Retrieval-Augmented Generation (RAG) have demonstrated powerful capabilities in generating counterspeech against misinformation. However, current studies rely on limited evidence and offer less control over final outputs. To address these challenges, we propose a Multi-agent Retrieval-Augmented Framework to generate counterspeech against health misinformation, incorporating multiple LLMs to optimize knowledge retrieval, evidence enhancement, and response refinement. Our approach integrates both static and dynamic evidence, ensuring that the generated counterspeech is relevant, well-grounded, and up-to-date. Our method outperforms baseline approaches in politeness, relevance, informativeness, and factual accuracy, demonstrating its effectiveness in generating high-quality counterspeech. To further validate our approach, we conduct ablation studies to verify the necessity of each component in our framework. Furthermore, cross evaluations show that our system generalizes well across diverse health misinformation topics and datasets. And human evaluations reveal that refinement significantly enhances counterspeech quality and obtains human preference. |
| title | Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.07307 |