Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Universal Adversarial Triggers
Benedict Florance Arockiaraj, Alexander Feng, Jianxiong Cai +1
Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a cl…
cs.CL2023
Linguistic Properties of Truthful Response
Bruce W. Lee, Benedict Florance Arockiaraj, Helen Jin
We investigate the phenomenon of an LLM's untruthful response using a large set of 220 handcrafted linguistic features. We focus on GPT-3 models and find that the linguistic profil…