Related papers: Increasing Robustness to Spurious Correlations usi…

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Neural networks are known to use spurious correlations such as background information for classification. While prior work has looked at spurious correlations that are widespread in the training data, in this work, we investigate how…

Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume that the few examples provided are always correctly labeled.…

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group…

Deep learning models are known to overfit and memorize spurious features in the training dataset. While numerous empirical studies have aimed at understanding this phenomenon, a rigorous theoretical framework to quantify it is still…

We explore the utilities of explicit negative examples in training neural language models. Negative examples here are incorrect words in a sentence, such as "barks" in "*The dogs barks". Neural language models are commonly trained only on…

Recent results in image classification and extractive question answering have observed that pre-trained models trained on less in-distribution data have better out-of-distribution performance. However, it is unclear how broadly these trends…

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Models that learn spurious correlations from training data often fail when deployed in new environments. While many methods aim to learn invariant representations to address this, they often underperform standard empirical risk minimization…

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…

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…

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…

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…

The NLP community typically relies on performance of a model on a held-out test set to assess generalization. Performance drops observed in datasets outside of official test sets are generally attributed to "out-of-distribution" effects.…

In this paper, we study learning in probabilistic domains where the learner may receive incorrect labels but can improve the reliability of labels by repeatedly sampling them. In such a setting, one faces the problem of whether the fixed…

Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains…

Supervised neural networks, which first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$, have achieved remarkable success in a wide range of natural language processing (NLP) tasks. Despite their…

Standard NLP benchmarks often fail to capture vulnerabilities stemming from dataset artifacts and spurious correlations. Contrast sets address this gap by challenging models near decision boundaries but are traditionally labor-intensive to…