Related papers: On the Robustness of Knowledge Editing for Detoxif…

Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the traditional research paradigm that investigates new…

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to…

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations. However, despite the recent advances in NLP, it…

Knowledge Editing (KE) for modifying factual knowledge in Large Language Models (LLMs) has been receiving increasing attention. However, existing knowledge editing methods are entity-centric, and it is unclear whether this approach is…

Large language models (LLMs) trained with canonical tokenization exhibit surprising robustness to non-canonical inputs such as character-level tokenization, yet the mechanisms underlying this robustness remain unclear. We study this…

Large language models have demonstrated remarkable proficiency in long and complex reasoning tasks. However, they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term \textit{reasoning rigidity}.…

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be…

Although large models have shown a strong capacity to solve large-scale problems in many areas including natural language and computer vision, their voluminous parameters are hard to deploy in a real-time system due to computational and…

Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language. While the progress is promising, it is currently unclear if these models…

Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory integration, often suffer from inconsistent evaluation…

Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible to manipulations. With this work, we aim to enhance the…

Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic…

We demonstrate that learning procedures that rely on aggregated labels, e.g., label information distilled from noisy responses, enjoy robustness properties impossible without data cleaning. This robustness appears in several ways. In the…

Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is…

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…

While Knowledge Editing (KE) has been widely explored in English, its behavior in morphologically rich languages like Arabic remains underexamined. In this work, we present the first study of Arabic KE. We evaluate four methods (ROME,…

Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact…

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the…