Related papers: Robustly Leveraging Prior Knowledge in Text Classi…
Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…
Given the abundance of applications of ranking in recent years, addressing fairness concerns around automated ranking systems becomes necessary for increasing the trust among end-users. Previous work on fair ranking has mostly focused on…
The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…
The spread of misinformation, propaganda, and flawed argumentation has been amplified in the Internet era. Given the volume of data and the subtlety of identifying violations of argumentation norms, supporting information analytics tasks,…
Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned…
Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite…
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where…
We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design…
Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by…
Explanation methods have emerged as an important tool to highlight the features responsible for the predictions of neural networks. There is mounting evidence that many explanation methods are rather unreliable and susceptible to malicious…
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…
Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric…
Deep learning based models have surpassed classical machine learning based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this…
Automatic text categorization is a complex and useful task for many natural language processing applications. Recent approaches to text categorization focus more on algorithms than on resources involved in this operation. In contrast to…
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…
With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the…
Downstream applications often require text classification models to be accurate and robust. While the accuracy of the state-of-the-art Language Models (LMs) approximates human performance, they often exhibit a drop in performance on noisy…
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…
While the traditional formulation of machine learning tasks is in terms of performance on average, in practice we are often interested in how well a trained model performs on rare or difficult data points at test time. To achieve more…
Recent work has shown success in incorporating pre-trained models like BERT to improve NLP systems. However, existing pre-trained models lack of causal knowledge which prevents today's NLP systems from thinking like humans. In this paper,…