Related papers: Gumbel Counterfactual Generation From Language Mod…

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to…

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However, most existing counterfactual methods have not been tested…

Automatic counterspeech generation methods have been developed to assist efforts in combating hate speech. Existing research focuses on generating counterspeech with linguistic attributes such as being polite, informative, and…

In this paper, we describe an approach for modelling causal reasoning in natural language by detecting counterfactuals in text using multi-head self-attention weights. We use pre-trained transformer models to extract contextual embeddings…

Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent…

We introduce an extension of team semantics which provides a framework for the logic of manipulationist theories of causation based on structural equation models, such as Woodward's and Pearl's; our causal teams incorporate (partial or…

Biased news contributes to societal polarization and is often reinforced by hostile reader comments, constituting a vital yet often overlooked aspect of news dissemination. Our study reveals that offensive comments support biased content,…

Counterfactual Data Augmentation (CDA) has been one of the preferred techniques for mitigating gender bias in natural language models. CDA techniques have mostly employed word substitution based on dictionaries. Although such…

Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change…

In recent years, sequence-to-sequence models have been very effective for end-to-end grammatical error correction (GEC). As creating human-annotated parallel corpus for GEC is expensive and time-consuming, there has been work on artificial…

We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a…

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human…

Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…

When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. However, there is no…

Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they…

We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM…