Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

Wu, Tongshuang; Ribeiro, Marco Túlio; Heer, Jeffrey; Weld, Daniel S.

doi:10.18653/v1/2021.acl-long.523

Cited by 93 publications

(104 citation statements)

References 44 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…At least for STS dataset, this consideration also guided our choice when setting these two hyperparameters. Such a human-in-the-loop process to tune explanations is also seen in prior works [35,36,53].…”

Section: G Hyperparametersmentioning

confidence: 55%

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners

Ramamurthy¹,

Dhurandhar²,

Wei³

et al. 2022

Preprint

View full text Add to dashboard Cite

Post-hoc explanations for black box models have been studied extensively in classification and regression settings. However, explanations for models that output similarity between two inputs have received comparatively lesser attention. In this paper, we provide model agnostic local explanations for similarity learners applicable to tabular and text data. We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner. We then propose analogies as a new form of explanation in machine learning. Here the goal is to identify diverse analogous pairs of examples that share the same level of similarity as the input pair and provide insight into (latent) factors underlying the model's prediction. The selection of analogies can optionally leverage feature attributions, thus connecting the two forms of explanation while still maintaining complementarity. We prove that our analogy objective function is submodular, making the search for good-quality analogies efficient. We apply the proposed approaches to explain similarities between sentences as predicted by a state-of-the-art sentence encoder, and between patients in a healthcare utilization application. Efficacy is measured through quantitative evaluations, a careful user study, and examples of explanations.

show abstract

Section: G Hyperparametersmentioning

confidence: 55%

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners

Ramamurthy¹,

Dhurandhar²,

Wei³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In this work we propose a hybrid workflow in which a language model generates a first draft of a dataset example, and a human edits that draft. Based on evidence that editing is faster than writing [57], this workflow allows us to collect examples more efficiently than through a purely human workflow, while ensuring that the examples are of a higher quality than those produced by a fully automated workflow.…”

Section: Dataset Curation Methodologymentioning

confidence: 99%

SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets

Yuan

Ippolito

Nikolaev

et al. 2021

Preprint

View full text Add to dashboard Cite

NLP researchers need more, higher-quality text datasets. Human-labeled datasets are expensive to collect, while datasets collected via automatic retrieval from the web such as WikiBio [32] are noisy and can include undesired biases. Moreover, data sourced from the web is often included in datasets used to pretrain models, leading to inadvertent cross-contamination of training and test sets. In this work we introduce a novel method for efficient dataset curation: we use a large language model to provide seed generations to human raters, thereby changing dataset authoring from a writing task to an editing task. We use our method to curate SynthBio-a new evaluation set for WikiBio-composed of structured attribute lists describing fictional individuals, mapped to natural language biographies. We show that our dataset of fictional biographies is less noisy than WikiBio, and also more balanced with respect to gender and nationality.

show abstract

“…where an explicit protected attribute is often not present. In these domains, counterfactual augmentation is generally a manual process; recent work provides support [31,42] but not complete automation. Prediction sensitivity (defined in Section 3) can be viewed as a way of measuring counterfactual fairness.…”

Section: Background and Related Workmentioning

confidence: 99%

Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers

Maughan¹,

Ngong²,

Near³

2022

Preprint

View full text Add to dashboard Cite

As AI-based systems increasingly impact many areas of our lives, auditing these systems for fairness is an increasingly high-stakes problem. Traditional group fairness metrics can miss discrimination against individuals and are difficult to apply after deployment.Counterfactual fairness describes an individualized notion of fairness, but is even more challenging to evaluate after deployment. We present prediction sensitivity, an approach for continual audit of counterfactual fairness in deployed classifiers. Prediction sensitivity helps answer the question: would this prediction have been different, if this individual had belonged to a different demographic group-for every prediction made by the deployed model. Prediction sensitivity can leverage correlations between protected status and other features, and does not require protected status information at prediction time. Our empirical results demonstrate that prediction sensitivity is effective for detecting violations of counterfactual fairness.

show abstract

Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

Cited by 93 publications

References 44 publications

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners

SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets

Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers

Contact Info

Product

Resources

About