A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

By Ilia Stepin, J. Alonso, Alejandro Catalá, Martin Pereira-Fariña. IEEE Access, 2021

385 citations recorded by the source corpus.

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

Subfields: Artificial Intelligence, Information Systems and Management

View Paper: https://www.semanticscholar.org/paper/e016ee7bfc73cb5b8a92f6c517389be837c035eb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

Citations in the corpus

Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “A further important point as observed by [56] that one of the significant barriers towards a fair assessment of new frameworks is the lack of standardization of evaluation methods.”
Survey of Explainable AI Techniques in Healthcare (2023, background): “, offer explanations from various perspectives, so that users have the option to choose explanations), and (3) counterfactual explanations to enhance human–computer interactions and produces personalized output with the AI model [105].”
Pre-Trained Language Models for Text Generation: A Survey (2022, methodology): “Explanation generation is designed to interpret AI algorithms, elucidating how models arrive at specific decisions to enhance users’ trust and augment the usability of the algorithms [221].”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, neutral): “[239] discuss XAI methods and their evaluation for contrastive and counterfactual explanations, Tintarev and Masthoff [250] and Nunes and Jannach [182] discuss explanations and their evaluation for recommender systems, and Markus et al.”