相关论文: Multi-head attention debiasing and contrastive lea…

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attention by allowing a model to jointly attend information from…

Natural Language Inference (NLI) is the task of determining whether a sentence pair represents entailment, contradiction, or a neutral relationship. While NLI models perform well on many inference tasks, their ability to handle fine-grained…

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Natural Language Inference (NLI) is considered a representative task to test natural language understanding (NLU). In this work, we propose an extensible framework to collectively yet categorically test diverse Logical reasoning…

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended underlying task. Previous work has demonstrated effective methods to…

Stereotypes influence social perceptions and can escalate into discrimination and violence. While NLP research has extensively addressed gender bias and hate speech, stereotype detection remains an emerging field with significant societal…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Language Identification (LID) is a core task in multilingual NLP, yet current systems often overfit to clean, monolingual data. This work introduces DIVERS-BENCH, a comprehensive evaluation of state-of-the-art LID models across diverse…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Scientific Natural Language Inference (NLI) is the task of predicting the semantic relation between a pair of sentences extracted from research articles. The automatic annotation method based on distant supervision for the training set of…

Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remains challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We propose a novel framework that combines Large…

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in…

Highly realistic AI generated face forgeries known as deepfakes have raised serious social concerns. Although DNN-based face forgery detection models have achieved good performance, they are vulnerable to latest generative methods that have…

Existing datasets for natural language inference (NLI) have propelled research on language understanding. We propose a new method for automatically deriving NLI datasets from the growing abundance of large-scale question answering datasets.…

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

How can neural networks trained by contrastive learning extract features from the unlabeled data? Why does contrastive learning usually need much stronger data augmentations than supervised learning to ensure good representations? These…