Towards trustworthy large language models
B Wang - 2023 - ideals.illinois.edu
In the recent era of artificial intelligence, Large Language Models (LLMs) have achieved
unprecedented success in a wide range of Natural Language Processing (NLP) tasks …
unprecedented success in a wide range of Natural Language Processing (NLP) tasks …
Debiasing stance detection models with counterfactual reasoning and adversarial bias learning
J Yuan, Y Zhao, B Qin - arXiv preprint arXiv:2212.10392, 2022 - arxiv.org
Stance detection models may tend to rely on dataset bias in the text part as a shortcut and
thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing …
thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing …
Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context
Abstract Machine Reading Comprehension (MRC) models easily learn spurious correlations
from complex contexts such as tabular data. Counterfactual training—using the factual and …
from complex contexts such as tabular data. Counterfactual training—using the factual and …