This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Foundational safety research, theoretical understanding, and scientific inquiry informing AI development.
Also in Engineering & Development
Research focusing on developing equitable AI systems, including detecting and mitigating bias, ensuring fair representation across diverse groups, addressing fairness in dynamic or constrained data scenarios, and reconciling conflicting fairness definitions to align interventions with societal values.
Reasoning
Foundational research into fairness mechanisms and bias detection to inform equitable AI system development.
Fairness under dynamic and constrained data scenarios
Ensuring that fairness interventions remain effective under continual learning, adaptive deployment, or evolving operational contexts.
2.4.1 Research & FoundationsFair representation and participation in AI systems
Promoting fair representation and generalization across different subpopulations, and ensuring inclusive participation in the development and governance of AI systems.
2.4.1 Research & FoundationsBias detection, quantification, and mitigation techniques
Developing systematic methods to detect, measure, and reduce bias in model outputs, ranging from pre-processing adjustments to post-hoc corrections. This may also include causal methods for fairness, such as causal modeling techniques to distinguish between genuine causal relationships and spurious correlations in observed disparities, enabling fairness interventions that address underlying structural causes.
1.1 ModelFairness in multilingual, cross-cultural, and multimodal contexts
Addressing fairness challenges that arise when models operate across different languages, cultures, and data modalities.
2.4.1 Research & FoundationsIntersectional fairness and complex group structures
Addressing compounded biases that arise when protected attributes overlap, such as race and gender, to ensure fairness approaches capture nuanced harms across intersectional groups. This research develops computational methods and evaluation frameworks to avoid oversimplifying population categories and to identify disparities affecting complex group structures.
2.4.1 Research & FoundationsReconciling multiple fairness definitions and normative trade-offs
Comparing and combining conflicting formal definitions of fairness to address the normative trade-offs they entail and align fairness interventions with societal values. This research clarifies the theoretical and practical implications of fairness definitions, helping practitioners navigate complex policy and ethical considerations.
2.4.1 Research & FoundationsTheoretical foundations and provable safety in AI systems
Advancing the theoretical foundations of AI safety by building models and frameworks that ensure provably correct and robust behavior. These efforts span from verifiable architectures and formal verification methods to embedded agency, decision theory, incentive structures aligned with causal reasoning, and control theory.
2.4.1 Research & FoundationsTheoretical foundations and provable safety in AI systems > Building verifiable and robust AI architectures
Constructing AI systems with architectures that support formal verification and robustness guarantees, such as world models that enable safe and reliable planning, or guaranteed safe AI with Bayesian oracles. This area emphasizes simplicity and transparency to aid in provability.
1.1.4 Model ArchitectureTheoretical foundations and provable safety in AI systems > Formal verification of AI systems
Applying formal methods to verify that AI models and algorithms meet stringent safety, robustness, and performance criteria. This includes proving resilience against adversarial inputs and perturbations, and certifying conformance to specified safety properties under varying conditions.
2.2.2 Testing & EvaluationTheoretical foundations and provable safety in AI systems > Decision theory and rational agency
Establishing formal decision-making frameworks that ensure rational and safe choices by AI agents, potentially drawing on concepts like causal and evidential decision theory.
2.4.1 Research & FoundationsTheoretical foundations and provable safety in AI systems > Embedded agency
Explores how agents can model and reason about themselves and their environment as interconnected parts of a single system, addressing challenges like self-reference, resource constraints, and the stability of reasoning processes. This includes tackling problems arising from the lack of a clear boundary between the agent and its environment.
2.4.1 Research & FoundationsTheoretical foundations and provable safety in AI systems > Causal incentives
Developing frameworks that formalize how to align agent incentives with safe and desired outcomes by ensuring their causal understanding matches intended objectives. This research provides a formal language for guaranteeing safety, addressing challenges like goal misspecification, and complementing broader efforts in agent foundations and robust system design.
2.4.1 Research & FoundationsExpert Survey: AI Reliability & Security Research Priorities
O'Brien, Joe; Dolan, Jeremy; Kim, Jay; Dykhuizen, Jonah; Sania, Jeba; Becker, Sebastian; Kraprayoon, Jam; Labrador, Cara (2025)
Our survey of 53 specialists across 105 AI reliability and security research areas identifies the most promising research prospects to guide strategic AI R&D investment. As companies are seeking to develop AI systems with broadly human-level capabilities, research on reliability and security is urgently needed to ensure AI's benefits can be safely and broadly realized and prevent severe harms. This study is the first to quantify expert priorities across a comprehensive taxonomy of AI safety and security research directions and to produce a data-driven ranking of their potential impact. These rankings may support evidence-based decisions about how to effectively deploy resources toward AI reliability and security research.
Other (outside lifecycle)
Outside the standard AI system lifecycle
Developer
Entity that creates, trains, or modifies the AI system
Other
Risk management function not captured by the standard AIRM categories
Other
