Related papers: Competency Problems: On Finding and Removing Artif…

In recent years, the availability of large-scale annotated datasets, such as the Stanford Natural Language Inference and the Multi-Genre Natural Language Inference, coupled with the advent of pre-trained language models, has significantly…

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.…

Ambiguity is a natural language phenomenon occurring at different levels of syntax, semantics, and pragmatics. It is widely studied; in Psycholinguistics, for instance, we have a variety of competing studies for the human disambiguation…

Spurious bias, a tendency to exploit spurious correlations between superficial input attributes and prediction targets, has revealed a severe robustness pitfall in classical machine learning problems. Multimodal Large Language Models…

Existing research often posits spurious features as easier to learn than core features in neural network optimization, but the impact of their relative simplicity remains under-explored. Moreover, studies mainly focus on end performance…

Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness…

In this paper we discuss the following issue: How do we decide whether a certain property of language is a competence property or a performance property? Our claim is that the answer to this question is not given a-priori. The answer…

Learning representations which remain invariant to a nuisance factor has a great interest in Domain Adaptation, Transfer Learning, and Fair Machine Learning. Finding such representations becomes highly challenging in NLP tasks since the…

Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern…

We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three different languages, we…

Large language models (LLMs) are increasingly used in decision-making tasks like r\'esum\'e screening and content moderation, giving them the power to amplify or suppress certain perspectives. While previous research has identified…

Several studies have shown that speech and language features, automatically extracted from clinical interviews or spontaneous discourse, have diagnostic value for mental disorders such as schizophrenia and bipolar disorder. They typically…

Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by…

Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that artificially inflate actual model performance. To address this,…

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization…

Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we define {\it core features} as the set of visual features that are…

In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that - especially given the well-known fact that benchmarks often…

Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can…

We analyze two Natural Language Inference data sets with respect to their linguistic features. The goal is to identify those syntactic and semantic properties that are particularly hard to comprehend for a machine learning model. To this…

Lexical ambiguity is widespread in language, allowing for the reuse of economical word forms and therefore making language more efficient. If ambiguous words cannot be disambiguated from context, however, this gain in efficiency might make…