English
Related papers

Related papers: Modeling AGI Safety Frameworks with Causal Influen…

200 papers

Causal structure learning with data from multiple contexts carries both opportunities and challenges. Opportunities arise from considering shared and context-specific causal graphs enabling to generalize and transfer causal knowledge across…

Machine Learning · Computer Science 2024-10-29 Martin Rabel , Wiebke Günther , Jakob Runge , Andreas Gerhardus

Directed acyclic graphs (DAGs) are commonly used to model causal relationships among random variables. In general, learning the DAG structure is both computationally and statistically challenging. Moreover, without additional information,…

Machine Learning · Statistics 2024-03-26 Ali Shojaie , Wenyu Chen

This paper works through the optimization of a real world planning problem, with a combination of a generative planning tool and an influence diagram solver. The problem is taken from an existing application in the domain of oil spill…

Artificial Intelligence · Computer Science 2013-02-18 John Mark Agosta

As autonomous agents powered by large language models (LLMs) continue to demonstrate potential across various assistive tasks, ensuring their safe and reliable behavior is crucial for preventing unintended consequences. In this work, we…

Artificial Intelligence · Computer Science 2025-07-02 Dongyoon Hahm , Woogyeol Jin , June Suk Choi , Sungsoo Ahn , Kimin Lee

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

Machine Learning · Computer Science 2022-02-18 Mengyue Yang , Xinyu Cai , Furui Liu , Xu Chen , Zhitang Chen , Jianye Hao , Jun Wang

Recent interest in the external validity of prediction models (i.e., the problem of different train and test distributions, known as dataset shift) has produced many methods for finding predictive distributions that are invariant to dataset…

Machine Learning · Statistics 2022-07-20 Adarsh Subbaswamy , Bryant Chen , Suchi Saria

The potential influence diagram is a generalization of the standard "conditional" influence diagram, a directed network representation for probabilistic inference and decision analysis [Ndilikilikesha, 1991]. It allows efficient inference…

Artificial Intelligence · Computer Science 2013-03-08 Ross D. Shachter , Pierre Ndilikilikesha

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

In the fundamental statistics course, students are taught to remember the well-known saying: "Correlation is not Causation". Till now, statistics (i.e., correlation) have developed various successful frameworks, such as Transformer and…

Artificial Intelligence · Computer Science 2023-11-22 Ning Xu , Yifei Gao , Hongshuo Tian , Yongdong Zhang , An-An Liu

AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit. Yet, there does not exist a single formal definition…

Artificial Intelligence · Computer Science 2026-05-05 Pablo de los Riscos , Fernando J. Corbacho , Michael A. Arbib

Evaluating the safety of an autonomous vehicle (AV) depends on the behavior of surrounding agents which can be heavily influenced by factors such as environmental context and informally-defined driving etiquette. A key challenge is in…

Robotics · Computer Science 2022-10-07 Karen Leung , Sushant Veer , Edward Schmerling , Marco Pavone

We describe a design-based framework for drawing causal inference in general randomized experiments. Causal effects are defined as linear functionals evaluated at unit-level potential outcome functions. Assumptions about the potential…

Methodology · Statistics 2025-08-15 Christopher Harshaw , Fredrik Sävje , Yitan Wang

Protecting the security of the train control system is a critical issue to ensure the safe and reliable operation of high-speed trains. Scientific modeling and analysis for the security risk is a promising way to guarantee system security.…

Systems and Control · Electrical Eng. & Systems 2025-10-01 Zikai Zhang

Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior in traffic interactions. Accurate and reliable prediction models enabling more efficient trajectory planning could make…

Robotics · Computer Science 2023-02-21 Julian Frederik Schumann , Jens Kober , Arkady Zgonnikov

This paper presents a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation [15]. By modeling factors such as road…

Systems and Control · Electrical Eng. & Systems 2026-04-09 Kiruthiga Chandra Shekar , Aliasghar Moj Arab

A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distinct from those of any individual. More generally, determining…

Artificial Intelligence · Computer Science 2026-05-04 Frederik Hytting Jørgensen , Sebastian Weichwald , Lewis Hammond

This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal…

Machine Learning · Computer Science 2025-11-12 Dharmateja Priyadarshi Uddandarao , Ravi Kiran Vadlamani

Faced with data-driven policies, individuals will manipulate their features to obtain favorable decisions. While earlier works cast these manipulations as undesirable gaming, recent works have adopted a more nuanced causal framing in which…

Machine Learning · Computer Science 2023-02-22 Tom Yan , Shantanu Gupta , Zachary Lipton

Semi-autonomous vehicles are increasingly serving critical functions in various settings from mining to logistics to defence. A key characteristic of such systems is the presence of the human (drivers) in the control loop. To ensure safety,…

Human-Computer Interaction · Computer Science 2013-01-03 Siraj Shaikh , Padmanabhan Krishnan