Related papers: Influence Tuning: Demoting Spurious Correlations v…

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives…

Many training data attribution (TDA) methods aim to estimate how a model's behavior would change if one or more data points were removed from the training set. Methods based on implicit differentiation, such as influence functions, can be…

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these goals by retrieving…

Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with the target labels, leading to incorrect predictions by the…

Prediction-Powered Inference (PPI) is a recently proposed statistical inference technique for parameter estimation that leverages pseudo-labels on both labeled and unlabeled data to construct an unbiased, low-variance estimator. In this…

Large language models are being widely used across industries to generate content that contributes directly to key performance metrics, such as conversion rates. Pretrained models, however, often fall short when it comes to aligning with…

In many classification datasets, the task labels are spuriously correlated with some input attributes. Classifiers trained on such datasets often rely on these attributes for prediction, especially when the spurious correlation is high, and…

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In existing interpretation methods for NLP, a word's importance is…

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious…

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Curriculum learning, a training technique where data is presented to the model in order of example difficulty (e.g., from simpler to more complex documents), has shown limited success for pre-training language models. In this work, we…

While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable spurious features rather than the core features that are genuinely correlated to the true label. In this…

Spurious correlations are a major source of errors for machine learning models, in particular when aiming for group-level fairness. It has been recently shown that a powerful approach to combat spurious correlations is to re-train the last…

Understanding the influence of a training instance on a neural network model leads to improving interpretability. However, it is difficult and inefficient to evaluate the influence, which shows how a model's prediction would be changed if a…

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches…

Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold. Recent works suggest fixing pretrained representations and training a classification head that does…

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hinder generalization.…