Comparing Explainable AI Techniques In Language Models: A Case Study For Fake News Detection in Portuguese
Open Access
- 20 January 2026
- journal article
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1) , 01-12
Abstract
Language models are widely used in natural language processing, but their complexity makes interpretation difficult, limiting their adoption in critical decision-making. This work explores Explainable Artificial Intelligence (XAI) techniques, such as LIME and Integrated Gradients (IG), to understand these models. The study evaluates the effectiveness of BERTimbau in classifying Portuguese news as true or fake, using the FakeRecogna and Fake.Br Corpus datasets. In the experiments, LIME proved to be easier to interpret than IG, and both methods showed limitations when applied to texts, as they focus only on the morphological and lexical levels, ignoring other important levels.Keywords
This publication has 13 references indexed in Scilit:
- Towards explainable automatic punctuation restoration for Portuguese using transformersExpert Systems with Applications, 2024
- Explainable Models for the Detection of Incidents of Fake News and Hate Speech2024
- Towards explainable prediction of essay cohesion in Portuguese and English2023
- FakeRecogna: A New Brazilian Corpus for Fake News Detection2022
- From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and WhereIEEE Transactions on Industrial Informatics, 2022
- Explainable Artificial Intelligence Approaches: Challenges and Perspectives2021
- Explaining Black-Box Models for Biomedical Text ClassificationIEEE Journal of Biomedical and Health Informatics, 2021
- BERTimbau: Pretrained BERT Models for Brazilian Portuguese2020
- Faithful and Customizable Explanations of Black Box Models2019
- "Why Should I Trust You?"2016