Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction
It addresses the problem of automated fact correction for misinformation on social media, offering a robust method that does not require supervised training data.
The paper proposes a training-free, inference-only RAG framework (M2C and M2C+) for faithful fact correction that uses diversity-aware masking to identify erroneous spans and evaluates correction faithfulness. It achieves up to 14% improvement in SARI scores on benchmark datasets without using gold evidence.
The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely on supervised learning from manually annotated claim-evidence pairs, which are scarce and prone to biases, limiting their generalization across domains. Moreover, these methods overlook semantic faithfulness in their correction process. To address these challenges, we propose Mask-to-Correct (M$_2$C), a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous spans of claims and evaluate the faithfulness of corrections using retrieved evidence. However, the effectiveness of RAG heavily depends on the choice of retriever, which may vary across queries. To mitigate this, we further introduce M$_2$C$^+$, an ensemble-based framework that combines corrections across multiple rankers to reduce retrieval bias and improve robustness. Extensive experiments on the benchmark datasets demonstrate that our proposed frameworks consistently outperform all baselines, achieving up to 14% improvement in SARI scores, without using gold evidence.