aiqbench analysis
This research addresses the robustness of fake news detection models against emotionally rewritten articles by leveraging LLM-generated explanations as stable factual anchors. The authors introduce a Gated Cross Attention framework that adaptively integrates these explanations to mitigate mismatches caused by emotional reframing, demonstrating improved performance on standard fact-checking datasets. This work is significant for advancing AI safety and reliability in misinformation detection systems under varying linguistic conditions.
Leveraging LLM-Generated Explanations for Detecting Emotionally Rewritten Fake News
arXiv:2610.08835v1 Announce Type: new Abstract: The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate external information such as explanations. However, news articles are often rewritten under different emotional backgrounds while preserving their underlying factual claims, which may affect the robustness of detection models. In this work, we investigate fake news detec- tion under fact-preserving emotional variations. To study this problem, we construct emotion-rewritten test sets and generate explanations from the original news articles as stable background knowledge. We then propose a Gated Cross Attention (GCA) framework that adaptively integrates emotionally rewritten news with the corresponding explanations, enabling the model to focus on informative explanation content while reducing potential mismatches caused by emotional reframing. Experiments on PolitiFact, GossipCop, and LUN demonstrate that the proposed method achieves notable improvements under multiple emotional conditions on PolitiFact and LUN, while maintaining competitive performance on GossipCop. We further analyze the effects of explanation guidance and gating mechanisms under different emotional conditions. Our code and data are available at: https://github.com/Flulike/fakenews gca .
Abstract:The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate external information such as explanations. However, news articles are often rewritten under different emotional backgrounds while preserving their underlying factual claims, which may affect the robustness of detection models. In this work, we investigate fake news detec- tion under fact-preserving emotional variations. To study this problem, we construct emotion-rewritten test sets and generate explanations from the original news articles as stable background knowledge. We then propose a Gated Cross Attention (GCA) framework that adaptively integrates emotionally rewritten news with the corresponding explanations, enabling the model to focus on informative explanation content while reducing potential mismatches caused by emotional reframing. Experiments on PolitiFact, GossipCop, and LUN demonstrate that the proposed method achieves notable improvements under multiple emotional conditions on PolitiFact and LUN, while maintaining competitive performance on GossipCop. We further analyze the effects of explanation guidance and gating mechanisms under different emotional conditions. Our code and data are available at: this https URL gca .
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2610.08835 [cs.CL]
(or arXiv:2610.08835v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.08835 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 272 words
Related coverage
News
Quantum Computing Report · Jun 7, 2026
Cross-Prompt Generalization in Detecting AI-Generated Fake News Using Interpretable Linguistic Features
arXiv · Jun 5, 2026
SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection
arXiv · Oct 12, 2026
I Did This Without Your Knowledge
LessWrong · Oct 17, 2026