Related papers: Avoiding spurious correlations via logit correctio…
Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…
Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward…
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…
Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…
We study binary classification in the setting where the learner is presented with multiple corrupted training samples, with possibly different sample sizes and degrees of corruption, and introduce an approach based on minimizing a weighted…
Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance. Existing methods often rely on predicted class probabilities…
In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the…
Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric…
Due to the inherent imbalance in real-world datasets, na\"ive Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning…
To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpensively at inference time. Unfortunately, commonly used approaches, including supervised and…
Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. The task is to learn a…
Emotion recognition in conversations (ERC) is a rapidly evolving task within the natural language processing community, which aims to detect the emotions expressed by speakers during a conversation. Recently, a growing number of ERC methods…
It is well-known that training neural networks for image classification with empirical risk minimization (ERM) makes them vulnerable to relying on spurious attributes instead of causal ones for prediction. Previously, deep feature…
In NLP, recent work has seen increased focus on spurious correlations between various features and labels in training data, and how these influence model behavior. However, the presence and effect of such correlations are typically examined…
Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…
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.…
Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances. This paper focuses on imbalanced classification datasets, in which a small subset…
This paper aims to provide a better understanding of a symmetric loss. First, we emphasize that using a symmetric loss is advantageous in the balanced error rate (BER) minimization and area under the receiver operating characteristic curve…
Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked…
In many applications, the training data, from which one needs to learn a classifier, is corrupted with label noise. Many standard algorithms such as SVM perform poorly in presence of label noise. In this paper we investigate the robustness…