Cover Image

Calibrating Conservatism for Scalable Oversight

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Overman, William, Bayati, Mohsen
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
by: Overman, William, et al.
Published: (2025)

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
by: Overman, William, et al.
Published: (2025)

Annealed Softmax Greedy in Many-Armed Bayesian Bandits
by: Overman, William, et al.
Published: (2026)

Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight
by: Ye, Junze, et al.
Published: (2025)

Simulating and Experimenting with Social Media Mobilization Using LLM Agents
by: Shirani, Sadegh, et al.
Published: (2025)

A Benchmark for Scalable Oversight Protocols
by: Sudhir, Abhimanyu Pallavi, et al.
Published: (2025)

Causal Effects with Unobserved Unit Types in Interacting Human-AI Systems
by: Overman, William, et al.
Published: (2026)

Scaling Laws For Scalable Oversight
by: Engels, Joshua, et al.
Published: (2025)

Steering LLMs via Scalable Interactive Oversight
by: Zhou, Enyu, et al.
Published: (2026)

Aligning Model Properties via Conformal Risk Control
by: Overman, William, et al.
Published: (2024)

Modeling Human Beliefs about AI Behavior for Scalable Oversight
by: Lang, Leon, et al.
Published: (2025)

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
by: Jin, Can, et al.
Published: (2026)

Towards Scalable Oversight via Partitioned Human Supervision
by: Yin, Ren, et al.
Published: (2025)

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
by: Wen, Xueru, et al.
Published: (2025)

FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research
by: Recchia, Gabriel, et al.
Published: (2025)

Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes
by: Faradonbeh, Mohamad Kazem Shirani, et al.
Published: (2022)

Quantile Regression with Large Language Models for Price Prediction
by: Vedula, Nikhita, et al.
Published: (2025)

Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning
by: Cho, Minjae, et al.
Published: (2024)

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
by: Song, Yeda, et al.
Published: (2024)

Higher-Order Causal Message Passing for Experimentation with Complex Interference
by: Bayati, Mohsen, et al.
Published: (2024)

Can We Validate Counterfactual Estimations in the Presence of General Network Interference?
by: Shirani, Sadegh, et al.
Published: (2025)

FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
by: Zhou, Jiayi, et al.
Published: (2026)

Scalable Utility-Aware Multiclass Calibration
by: Hegazy, Mahmoud, et al.
Published: (2025)

Oversight Structures for Agentic AI in Public-Sector Organizations
by: Schmitz, Chris, et al.
Published: (2025)

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
by: Cui, Christopher Z., et al.
Published: (2026)

Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions
by: Mamman, Hussaini, et al.
Published: (2024)

Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety
by: Kim, Yubin, et al.
Published: (2025)

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
by: Beltoft, Stine Lyngsø, et al.
Published: (2026)

AI and Human Oversight: A Risk-Based Framework for Alignment
by: Kandikatla, Laxmiraju, et al.
Published: (2025)

Overseeing Agents Without Constant Oversight: Challenges and Opportunities
by: Grunde-McLaughlin, Madeleine, et al.
Published: (2026)

Human-AI Complementarity: A Goal for Amplified Oversight
by: Jain, Rishub, et al.
Published: (2025)

Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems
by: Lermen, Simon, et al.
Published: (2025)

PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity Oversight
by: Goertzel, Ben, et al.
Published: (2025)

Great Models Think Alike and this Undermines AI Oversight
by: Goel, Shashwat, et al.
Published: (2025)

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
by: Li, Wenkai, et al.
Published: (2026)

Quantifying Automation Risk in High-Automation AI Systems: A Bayesian Framework for Failure Propagation and Optimal Oversight
by: Srivastava, Vishal, et al.
Published: (2026)

Hierarchical Pedagogical Oversight: A Multi-Agent Adversarial Framework for Reliable AI Tutoring
by: Sadhu, Saisab, et al.
Published: (2025)

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
by: Li, Albus Yizhuo, et al.
Published: (2026)

Exploring Moral Exercises for Human Oversight of AI systems: Insights from Three Pilot Studies
by: Crafa, Silvia, et al.
Published: (2025)

Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting
by: Klößner, Thorsten, et al.
Published: (2026)