Rishanth Rajendhran
YOU?
Author Swipe
View article: VeriFastScore: Speeding up long-form factuality evaluation
VeriFastScore: Speeding up long-form factuality evaluation Open
Metrics like FactScore and VeriScore that evaluate long-form factuality operate by decomposing an input response into atomic claims and then individually verifying each claim. While effective and interpretable, these methods incur numerous…
View article: Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness
Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness Open
Do larger and more performant models resolve NLP's longstanding robustness issues? We investigate this question using over 20 models of different sizes spanning different architectural choices and pretraining objectives. We conduct evaluat…