Human-annotated rationales and explainable text classification: a survey

E Herrewijnen, D Nguyen, F Bex… - Frontiers in Artificial …, 2024 - frontiersin.org
Asking annotators to explain “why” they labeled an instance yields annotator rationales:
natural language explanations that provide reasons for classifications. In this work, we …

Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers

LN Tung, S Cho, X Du, N Neelofar, V Terragni… - arxiv preprint arxiv …, 2024 - arxiv.org
Machine learning (ML) for text classification has been widely used in various domains, such
as toxicity detection, chatbot consulting, and review analysis. These applications can …

[HTML][HTML] Learning to generate and evaluate fact-checking explanations with transformers

D Feher, A Khered, H Zhang, R Batista-Navarro… - … Applications of Artificial …, 2025 - Elsevier
In an era increasingly dominated by digital platforms, the spread of misinformation poses a
significant challenge, highlighting the need for solutions capable of assessing information …

Challenges in explanation quality evaluation

H Schuff, H Adel, P Qi, NT Vu - arxiv preprint arxiv:2210.07126, 2022 - arxiv.org
While much research focused on producing explanations, it is still unclear how the produced
explanations' quality can be evaluated in a meaningful way. Today's predominant approach …

[PDF][PDF] Human-centered explainable artificial intelligence for natural language processing

H Schuff - 2024 - d-nb.info
AI and NLP Systems. AI systems affect nearly every aspect of our digital lives:
Recommender systems determine which media content we are shown (Covington et al …

[PDF][PDF] 16th International AAAI Conference on Web and Social Media

J Pfeffer - 2022 - researchgate.net
Abstract The International AAAI Conference on Web and Social Media (ICWSM) is a forum
for researchers from multiple disciplines to come together to share knowledge, discuss …