English
Related papers

Related papers: Counterfactual Harm: A Counter-argument

200 papers

To act safely and ethically in the real world, agents must be able to reason about harm and avoid harmful actions. However, to date there is no statistical method for measuring harm and factoring it into algorithmic decisions. In this paper…

Artificial Intelligence · Computer Science 2022-11-03 Jonathan G. Richens , Rory Beard , Daniel H. Thompson

In our original article (Sarvet & Stensrud, 2024), we examine twin definitions of "harm" in personalized medicine: one based on predictions of individuals' unmeasurable response types (counterfactual harm), and another based solely on the…

Applications · Statistics 2024-03-25 Aaron L. Sarvet , Mats J. Stensrud

Avoiding harm is an uncontroversial aim of personalized medicine and other epidemiologic initiatives. However, the precise mathematical translation of "harm" is disputable. Here we use a formal causal language to study common, but distinct,…

Applications · Statistics 2024-01-10 Aaron L. Sarvet , Mats J. Stensrud

As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles:…

Machine Learning · Computer Science 2026-02-25 Sima Noorani , Shayan Kiyani , Hamed Hassani , George Pappas

Counterfactuals and counterfactual reasoning underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is the interventional…

Artificial Intelligence · Computer Science 2024-01-26 Lucius E. J. Bynum , Joshua R. Loftus , Julia Stoyanovich

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework to address when and how such a system harms someone. There have been several attempts within the philosophy literature to define…

Artificial Intelligence · Computer Science 2023-01-20 Sander Beckers , Hana Chockler , Joseph Y. Halpern

NeurIPS 2020 requested that research paper submissions include impact statements on "potential nefarious uses and the consequences of failure." However, as researchers, practitioners and system designers, a key challenge to anticipating…

Computers and Society · Computer Science 2020-12-11 Margarita Boyarskaya , Alexandra Olteanu , Kate Crawford

In earlier work we defined a qualitative notion of harm: either harm is caused, or it is not. For practical applications, we often need to quantify harm; for example, we may want to choose the least harmful of a set of possible…

Artificial Intelligence · Computer Science 2026-05-07 Sander Beckers , Hana Chockler , Joseph Y. Halpern

Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, all common…

Artificial Intelligence · Computer Science 2022-07-20 Silvan Mertes , Christina Karle , Tobias Huber , Katharina Weitz , Ruben Schlagowski , Elisabeth André

AI-driven outcomes can be challenging for end-users to understand. Explanations can address two key questions: "Why this outcome?" (factual) and "Why not another?" (counterfactual). While substantial efforts have been made to formalize…

Artificial Intelligence · Computer Science 2025-03-21 Suryani Lim , Henri Prade , Gilles Richard

Reinforcement learning algorithms are generally designed to maximize the expected return across a population. However, a policy that is optimal on average may be suboptimal for certain individuals, leading to potential safety concerns. To…

Machine Learning · Statistics 2026-05-26 Jingyi Li , Peng Wu , Chengchun Shi

Harm is invoked everywhere from cybersecurity, ethics, risk analysis, to adversarial AI, yet there exists no systematic or agreed upon list of harms, and the concept itself is rarely defined with the precision required for serious analysis.…

Computers and Society · Computer Science 2026-01-26 Javed I. Khan , Sharmila Rahman Prithula

As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a…

Machine Learning · Computer Science 2020-10-09 Amir-Hossein Karimi , Bernhard Schölkopf , Isabel Valera

Hazard serves as a pivotal estimand in both practical applications and methodological frameworks. However, its causal interpretation poses notable challenges, including inherent selection biases and ill-defined populations to be compared…

Methodology · Statistics 2024-05-08 En-Yu Lai , Yen-Tsung Huang

The fundamental problem of causal inference -- that we never observe counterfactuals -- prevents us from identifying how many might be negatively affected by a proposed intervention. If, in an A/B test, half of users click (or buy, or…

Methodology · Statistics 2022-11-22 Nathan Kallus

Machine learning promises to revolutionize clinical decision making and diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms by determining the diseases \emph{causing} them. However, existing diagnostic algorithms…

Machine Learning · Statistics 2020-03-17 Jonathan G. Richens , Ciaran M. Lee , Saurabh Johri

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made…

Machine Learning · Statistics 2018-03-09 Matt J. Kusner , Joshua R. Loftus , Chris Russell , Ricardo Silva

The field of explainability in artificial intelligence (AI) has witnessed a growing number of studies and increasing scholarly interest. However, the lack of human-friendly and individual interpretations in explaining the outcomes of…

Artificial Intelligence · Computer Science 2025-02-04 Toygar Tanyel , Serkan Ayvaz , Bilgin Keserci

Decision support systems based on prediction sets help humans solve multiclass classification tasks by narrowing down the set of potential label values to a subset of them, namely a prediction set, and asking them to always predict label…

Machine Learning · Computer Science 2024-12-05 Eleni Straitouri , Suhas Thejaswi , Manuel Gomez Rodriguez

We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system's data inputs that causally drives the decision (i.e.,…

Machine Learning · Computer Science 2021-10-14 Carlos Fernández-Loría , Foster Provost , Xintian Han
‹ Prev 1 2 3 10 Next ›