English
Related papers

Related papers: Counterfactual Planning in AGI Systems

200 papers

As humans come to rely on autonomous systems more, ensuring the transparency of such systems is important to their continued adoption. Explainable Artificial Intelligence (XAI) aims to reduce confusion and foster trust in systems by…

Artificial Intelligence · Computer Science 2024-04-01 Benjamin Kraske , Zakariya Laouar , Zachary Sunberg

Machine learning is increasingly applied in high-stakes decision making that directly affect people's lives, and this leads to an increased demand for systems to explain their decisions. Explanations often take the form of counterfactuals,…

Machine Learning · Computer Science 2021-05-20 Maximilian Schleich , Zixuan Geng , Yihong Zhang , Dan Suciu

Counterfactuals are widely used in AI to explain how minimal changes to a model's input can lead to a different output. However, established methods for computing counterfactuals typically focus on one-step decision-making, and are not…

Artificial Intelligence · Computer Science 2025-05-15 Paul Kobialka , Lina Gerlach , Francesco Leofante , Erika Ábrahám , Silvia Lizeth Tapia Tarifa , Einar Broch Johnsen

We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an…

Robotics · Computer Science 2020-09-23 Simón C. Smith , Subramanian Ramamoorthy

Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains…

Machine Learning · Computer Science 2022-12-20 Eoin Delaney , Arjun Pakrashi , Derek Greene , Mark T. Keane

Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they…

Artificial Intelligence · Computer Science 2024-02-08 Sopam Dasgupta , Farhad Shakerin , Joaquín Arias , Elmer Salazar , Gopal Gupta

Large language model (LLM)-powered agents can translate high-level user intents into plans and actions in an environment. Yet after observing an outcome, users may wonder: What if I had phrased my intent differently? We introduce a…

Artificial Intelligence · Computer Science 2026-01-30 Amirmohammad Farzaneh , Salvatore D'Oro , Osvaldo Simeone

Counterfactual explanations are an increasingly popular form of post hoc explanation due to their (i) applicability across problem domains, (ii) proposed legal compliance (e.g., with GDPR), and (iii) reliance on the contrastive nature of…

Artificial Intelligence · Computer Science 2023-03-17 Greta Warren , Mark T. Keane , Christophe Gueret , Eoin Delaney

Counterfactual explanations are increasingly used as an Explainable Artificial Intelligence (XAI) technique to provide stakeholders of complex machine learning algorithms with explanations for data-driven decisions. The popularity of…

Artificial Intelligence · Computer Science 2023-04-26 Dieter Brughmans , Lissa Melis , David Martens

Counterfactual explanations are attracting significant attention due to the flourishing applications of machine learning models in consequential domains. A counterfactual plan consists of multiple possibilities to modify a given instance so…

Machine Learning · Computer Science 2022-04-12 Ngoc Bui , Duy Nguyen , Viet Anh Nguyen

While it is still unclear if agents with Artificial General Intelligence (AGI) could ever be built, we can already use mathematical models to investigate potential safety systems for these agents. We present an AGI safety layer that creates…

Artificial Intelligence · Computer Science 2020-07-13 Koen Holtman

Generating safety-critical driving scenarios requires understanding why dangerous interactions arise, rather than merely forcing collisions. However, existing methods rely on heuristic adversarial agent selection and unstructured…

Robotics · Computer Science 2026-03-24 Bowen Jing , Ruiyang Hao , Weitao Zhou , Haibao Yu

In recent years, considerable work has been done to tackle the issue of designing control laws based on observations to allow unknown dynamical systems to perform pre-specified tasks. At least as important for autonomy, however, is the…

Optimization and Control · Mathematics 2020-05-06 Luiz F. O. Chamon , Santiago Paternain , Alejandro Ribeiro

Machine-learning models are increasingly driving decisions in high-stakes settings, such as finance, law, and hiring, thus, highlighting the need for transparency. However, the key challenge is to balance transparency -- clarifying `why' a…

Artificial Intelligence · Computer Science 2025-08-29 Sopam Dasgupta , Sadaf MD Halim , Joaquín Arias , Elmer Salazar , Gopal Gupta

Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform…

Machine Learning · Statistics 2020-01-13 Amanda Coston , Alan Mishler , Edward H. Kennedy , Alexandra Chouldechova

Counterfactuals are a concept inherited from the field of logic and in general attain to the existence of causal relations between sentences or events. In particular, this concept has been introduced also in the context of interpretability…

Systems and Control · Electrical Eng. & Systems 2025-01-23 Pierluigi Francesco De Paola , Jared Miller , Alessandro Borri , Alessia Paglialonga , Fabrizio Dabbene

Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning…

Machine Learning · Statistics 2018-02-02 Peter Schulam , Suchi Saria

Counterfactual explanations study what should have changed in order to get an alternative result, enabling end-users to understand machine learning mechanisms with counterexamples. Actionability is defined as the ability to transform the…

Artificial Intelligence · Computer Science 2025-08-05 Enrique Valero-Leal , Pedro Larrañaga , Concha Bielza

Counterfactual thinking is a crucial yet challenging topic for artificial intelligence to learn knowledge from data and ultimately improve performance for new scenarios. Many research works, including the Potential Outcome Model (POM) and…

Artificial Intelligence · Computer Science 2026-02-24 Mingyu Kang , Duxin Chen , Ziyuan Pu , Jianxi Gao , Wenwu Yu

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

Artificial Intelligence · Computer Science 2026-01-06 Bin Xu