Benchmarking AI risk behaviors
cs.AI, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-13
Terminology
Sources
- Risk Alignment in Agentic AI Systems
- Optimal Policies Tend to Seek Power
- Risks from Learned Optimization in Advanced Machine Learning Systems
- Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
- Beyond Mimicry: Preference Coherence in LLMs
- AI as Decision-Maker: Ethics and Risk Preferences of LLMs
- LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory
- Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews
- When Do LLM Preferences Predict Downstream Behavior?
- Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
- Large Language Models Often Know When They Are Being Evaluated
- Risk Profiling and Modulation for LLMs
- Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty
- The Innate Economic Preferences of Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents