TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing

Among the existing eXplainable AI (XAI) approaches, Feature Attribution methods are a popular option due to their interpretable nature. However, each method leads to a different solution, thus introducing uncertainty regarding their reliability and coherence with respect to the underlying model. Thi...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Ettore Mariotti, Anna Arias-Duart, Michele Cafagna, Albert Gatt, Dario Garcia-Gasulla, Jose Maria Alonso-Moral
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2024-01-01
Edice:	IEEE Access
Témata:	Artificial intelligence (AI) explainable AI (XAI) trustworthy AI explanation faithfulness feature attribution feature importance
On-line přístup:	https://ieeexplore.ieee.org/document/10543008/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!