Image de couverture de livre

Modeling Human Beliefs about AI Behavior for Scalable Oversight

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lang, Leon, Forré, Patrick
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
par: Fluri, Lukas, et autres
Publié: (2024)

Towards Scalable Oversight via Partitioned Human Supervision
par: Yin, Ren, et autres
Publié: (2025)

Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks
par: Liu, Cong, et autres
Publié: (2024)

Steering LLMs via Scalable Interactive Oversight
par: Zhou, Enyu, et autres
Publié: (2026)

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
par: Wen, Xueru, et autres
Publié: (2025)

Scaling Laws For Scalable Oversight
par: Engels, Joshua, et autres
Publié: (2025)

On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration
par: Yu, Guanghui, et autres
Publié: (2024)

Clifford Group Equivariant Diffusion Models for 3D Molecular Generation
par: Liu, Cong, et autres
Publié: (2025)

Great Models Think Alike and this Undermines AI Oversight
par: Goel, Shashwat, et autres
Publié: (2025)

Early-Exit Neural Networks with Nested Prediction Sets
par: Jazbec, Metod, et autres
Publié: (2023)

Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
par: Federici, Marco, et autres
Publié: (2023)

The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
par: Overman, William, et autres
Publié: (2025)

Clifford-Steerable Convolutional Neural Networks
par: Zhdanov, Maksim, et autres
Publié: (2024)

AdS-GNN -- a Conformally Equivariant Graph Neural Network
par: Zhdanov, Maksim, et autres
Publié: (2025)

Building a Precise Video Language with Human-AI Oversight
par: Lin, Zhiqiu, et autres
Publié: (2026)

A Descriptive and Normative Theory of Human Beliefs in RLHF
par: Dandekar, Sylee, et autres
Publié: (2025)

Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving
par: Pham, Hung Cuong, et autres
Publié: (2026)

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
par: Lang, Leon, et autres
Publié: (2024)

Scalable Valuation of Human Feedback through Provably Robust Model Alignment
par: Fujisawa, Masahiro, et autres
Publié: (2025)

Deep Belief Markov Models for POMDP Inference
par: Arcieri, Giacomo, et autres
Publié: (2025)

Model Science: getting serious about verification, explanation and control of AI systems
par: Biecek, Przemyslaw, et autres
Publié: (2025)

BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination
par: Hao, Xin, et autres
Publié: (2024)

Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
par: Trivedi, Rakshit, et autres
Publié: (2026)

Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
par: Erden, Zeki Doruk, et autres
Publié: (2025)

Belief Aided Navigation using Bayesian Reinforcement Learning for Avoiding Humans in Blind Spots
par: Kim, Jinyeob, et autres
Publié: (2024)

Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
par: Liu, Xinge, et autres
Publié: (2026)

NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
par: Liao, Huan, et autres
Publié: (2025)

Conceptual Belief-Informed Reinforcement Learning
par: Gu, Xingrui, et autres
Publié: (2024)

Differentiable Belief-based Opponent Shaping
par: Sane, Aarav G, et autres
Publié: (2026)

MC-DBN: A Deep Belief Network-Based Model for Modality Completion
par: Luo, Zihong, et autres
Publié: (2024)

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
par: Feng, Lang, et autres
Publié: (2025)

Scalable Equilibrium Sampling with Sequential Boltzmann Generators
par: Tan, Charlie B., et autres
Publié: (2025)

Circular Belief Propagation for Approximate Probabilistic Inference
par: Bouttier, Vincent, et autres
Publié: (2024)

Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
par: Yan, Hua, et autres
Publié: (2026)

Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
par: Fan, Jiajun, et autres
Publié: (2023)

Discovering Behavioral Predispositions in Data to Improve Human Activity Recognition
par: Popko, Maximilian, et autres
Publié: (2022)

Selecting Belief-State Approximations in Simulators with Latent States
par: Jiang, Nan
Publié: (2025)

Heuristic Transformer: Belief Augmented In-Context Reinforcement Learning
par: Dippel, Oliver, et autres
Publié: (2025)

How to Explore with Belief: State Entropy Maximization in POMDPs
par: Zamboni, Riccardo, et autres
Publié: (2024)

Belief or Circuitry? Causal Evidence for In-Context Graph Learning
par: Kowalyshyn, Katharine, et autres
Publié: (2026)