Related papers: Generating Data to Mitigate Spurious Correlations …

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---while still failing on…

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of…

The performance of algorithmic decision rules is largely dependent on the quality of training datasets available to them. Biases in these datasets can raise economic and ethical concerns due to the resulting algorithms' disparate treatment…

While Natural Language Inference (NLI) models have achieved high performances on benchmark datasets, there are still concerns whether they truly capture the intended task, or largely exploit dataset artifacts. Through detailed analysis of…

Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting spurious correlations, or…

While large language models (LLMs) have demonstrated remarkable capabilities in language modeling, recent studies reveal that they often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.…

It is a strong prerequisite to access source data freely in many existing unsupervised domain adaptation approaches. However, source data is agnostic in many practical scenarios due to the constraints of expensive data transmission and data…

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to…

Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive information is semantically entangled with the task…

While synthetic data hold great promise for privacy protection, their statistical analysis poses significant challenges that necessitate innovative solutions. The use of deep generative models (DGMs) for synthetic data generation is known…

Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as…

Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural…

Handling imbalance in class distribution when building a classifier over tabular data has been a problem of long-standing interest. One popular approach is augmenting the training dataset with synthetically generated data. While classical…

Neural networks often make predictions relying on the spurious correlations from the datasets rather than the intrinsic properties of the task of interest, facing sharp degradation on out-of-distribution (OOD) test data. Existing de-bias…

Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…

NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely…

Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning. Although there are several algorithms proposed to mitigate it, we are yet to jointly derive the…

Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…

To enhance group robustness to spurious correlations, prior work often relies on auxiliary group annotations and assumes identical sets of groups across training and test domains. To overcome these limitations, we propose to leverage…

Deep neural networks trained with Empirical Risk Minimization (ERM) perform well when both training and test data come from the same domain, but they often fail to generalize to out-of-distribution samples. In image classification, these…