Improving model adversarial robustness in Extractive Question Answering via Wasserstein-Guided feature Representations
Extractive Question Answering (EQA) models aim to locate accurate answers from passages given a question but are highly susceptible to adversarial attacks. Existing adversarial training methods improve robustness by generating perturbed passages, yet they remain computationally expensive and prone t...
Zapisane w:
| Główni autorzy: | , , |
|---|---|
| Format: | Artigo |
| Język: | Inglês |
| Wydane: |
Elsevier
2025-09-01
|
| Seria: | Alexandria Engineering Journal |
| Hasła przedmiotowe: | |
| Dostęp online: | http://www.sciencedirect.com/science/article/pii/S1110016825006155 |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|