Advancements in artificial intelligence are rapidly increasing. The new‐generation large
language models, such as ChatGPT and GPT‐4, bear the potential to transform educational …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Fact-checking has become increasingly important due to the speed with which both
information and misinformation can spread in the modern media ecosystem. Therefore …

Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

Shortcut Learning of Large Language Models in Natural Language Understanding Page 1 110
COMMUNICATIONS OF THE ACM | JANUARY 2024 | VOL. 67 | NO. 1 research IMA GE B Y …

Neural networks trained with SGD were recently shown to rely preferentially on linearly-
predictive features and can ignore complex, equally-predictive ones. This simplicity bias can …

Existing methods for isolating hard subpopulations and spurious correlations in datasets
often require human intervention. This can make these methods labor-intensive and dataset …

Recent studies indicate that NLU models are prone to rely on shortcut features for prediction,
without achieving true language understanding. As a result, these models fail to generalize …

Recent research shows that pre-trained language models (PLMs) suffer from" prompt bias"
in factual knowledge extraction, ie, prompts tend to introduce biases toward specific labels …