Saved in:
Bibliographic Details
Main Authors: Xu, Xiaofei, Zhang, Xiuzhen, Deng, Ke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912417293795328
author Xu, Xiaofei
Zhang, Xiuzhen
Deng, Ke
author_facet Xu, Xiaofei
Zhang, Xiuzhen
Deng, Ke
contents 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 LLM prompt templates are at https://github.com/xxfwin/MisMitiFact.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques
Xu, Xiaofei
Zhang, Xiuzhen
Deng, Ke
Computation and Language
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 LLM prompt templates are at https://github.com/xxfwin/MisMitiFact.
title Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques
topic Computation and Language
url https://arxiv.org/abs/2506.05924