Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Chapanin, Alexander"'
Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2310.00603
Autor:
Calderon, Nitay, Porat, Naveh, Ben-David, Eyal, Chapanin, Alexander, Gekhman, Zorik, Oved, Nadav, Shalumov, Vitaly, Reichart, Roi
Existing research on Domain Robustness (DR) suffers from disparate setups, limited task variety, and scarce research on recent capabilities such as in-context learning. Furthermore, the common practice of measuring DR might not be fully accurate. Cur
Externí odkaz:
http://arxiv.org/abs/2306.00168