S-GBT introduces a Hessian-bounding tensor and associated regularization for LSTM and CNN models that yields tighter certified robustness bounds against word substitutions, improving robust accuracy by up to 23.4%.
arXiv preprint arXiv:2405.02764 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
LLMs show significant biases in conflict event classification, with open-weight models exhibiting false illegitimation and adapted models showing actor bias and lexical sensitivity, making them unsuitable for unsupervised deployment.
Molecular LLMs suffer large performance drops from single graph edits; in-context tuning on similar molecules partially widens their reliable region.
citing papers explorer
-
S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
S-GBT introduces a Hessian-bounding tensor and associated regularization for LSTM and CNN models that yields tighter certified robustness bounds against word substitutions, improving robust accuracy by up to 23.4%.
-
Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africa
LLMs show significant biases in conflict event classification, with open-weight models exhibiting false illegitimation and adapted models showing actor bias and lexical sensitivity, making them unsuitable for unsupervised deployment.
-
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
Molecular LLMs suffer large performance drops from single graph edits; in-context tuning on similar molecules partially widens their reliable region.