---
title: "Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques"
authors:
  - "Xiaofei Xu"
  - "Xiuzhen Zhang"
  - "Ke Deng"
doi: "10.24963/ijcai.2025/1047"
url: "https://ijcai.org/proceedings/2025/1047"
pdf: "https://ijcai.org/proceedings/2025/1047.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "9420-9428"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Social and AI4Society"
  - "Domain-specific AI4Tech: AI4Safety"
---

# Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques

Xiaofei Xu, Xiuzhen Zhang, Ke Deng

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 9420-9428. DOI: [10.24963/ijcai.2025/1047](https://doi.org/10.24963/ijcai.2025/1047)

## Abstract

Fake news and misinformation poses a significant threat to society, making efficient mitigation essential. However, manual fact-checking is costly and lacks scalability. Large Language Models (LLMs) offer promise in automating counter-response generation to mitigate misinformation, but a critical challenge lies in their tendency to hallucinate non-factual information. Existing models mainly rely on LLM self-feedback to reduce hallucination, but this approach is computationally expensive. In this paper, we propose MisMitiFact, Misinformation Mitigation grounded in Facts, an efficient framework for generating fact-grounded counter-responses at scale. MisMitiFact generates simple critique feedback to refine LLM outputs, ensuring responses are grounded in evidence. 
We develop lightweight, fine-grained critique models trained on data sourced from readily available fact-checking sites to identify and correct errors in key elements such as numerals, entities, and topics in LLM generations. Experiments show that MisMitiFact generates counter-responses of comparable quality to LLMs' self-feedback while using significantly smaller critique models. Importantly, it achieves ~5x increase in feedback generation throughput, making it highly suitable for cost-effective, large-scale misinformation mitigation. Code and additional results are available at https://github.com/xxfwin/MisMitiFact.