2025
Refining Attention for Explainable and Noise-Robust Fact-Checking with Transformers
EMNLP 2025
In tasks like question answering and fact-checking, models must discern relevant information from extensive corpora in an “open-book” setting. Conventional transformer-based models excel at classifying input data, but (i) often falter due to sensitivity to noise and (ii) lack explainability regardin