Cover Image

Evaluating Frontier Models for Stealth and Situational Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Phuong, Mary, Zimmermann, Roland S., Wang, Ziyue, Lindner, David, Krakovna, Victoria, Cogan, Sarah, Dafoe, Allan, Ho, Lewis, Shah, Rohin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Realistic honeypot evaluations for scheming propensity
by: Krakovna, Victoria, et al.
Published: (2026)

Evaluating Frontier Models for Dangerous Capabilities
by: Phuong, Mary, et al.
Published: (2024)

Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
by: Kaufmann, Max, et al.
Published: (2026)

Gram: Assessing sabotage propensities via automated alignment auditing
by: Lindner, David, et al.
Published: (2026)

A Pragmatic Way to Measure Chain-of-Thought Monitorability
by: Emmons, Scott, et al.
Published: (2025)

Early Signs of Steganographic Capabilities in Frontier LLMs
by: Zolkowski, Artur, et al.
Published: (2025)

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
by: Farquhar, Sebastian, et al.
Published: (2025)

Frontier Models Can Take Actions at Low Probabilities
by: Serrano, Alex, et al.
Published: (2026)

MISR: Measuring Instrumental Self-Reasoning in Frontier Models
by: Fronsdal, Kai, et al.
Published: (2024)

An Approach to Technical AGI Safety and Security
by: Shah, Rohin, et al.
Published: (2025)

Evaluating the Goal-Directedness of Large Language Models
by: Everitt, Tom, et al.
Published: (2025)

AtP*: An efficient and scalable method for localizing LLM behaviour to components
by: Kramár, János, et al.
Published: (2024)

Improving Water Quality Time-Series Prediction in Hong Kong using Sentinel-2 MSI Data and Google Earth Engine Cloud Computing
by: Sood, Rohin, et al.
Published: (2024)

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
by: Korbak, Tomek, et al.
Published: (2025)

Holistic Safety and Responsibility Evaluations of Advanced AI Models
by: Weidinger, Laura, et al.
Published: (2024)

Consistency Training Helps Stop Sycophancy and Jailbreaks
by: Irpan, Alex, et al.
Published: (2025)

Improving Dictionary Learning with Gated Sparse Autoencoders
by: Rajamanoharan, Senthooran, et al.
Published: (2024)

On scalable oversight with weak LLMs judging strong LLMs
by: Kenton, Zachary, et al.
Published: (2024)

Sabotage Evaluations for Frontier Models
by: Benton, Joe, et al.
Published: (2024)

Frontier Models are Capable of In-context Scheming
by: Meinke, Alexander, et al.
Published: (2024)

The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
by: Kao, Ching-Chia, et al.
Published: (2024)

Will You Be Aware? Eye Tracking-Based Modeling of Situational Awareness in Augmented Reality
by: Qu, Zhehan, et al.
Published: (2025)

From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction
by: Liu, Anqi, et al.
Published: (2026)

Exploration Hacking: Can LLMs Learn to Resist RL Training?
by: Jang, Eyon, et al.
Published: (2026)

Situationally-Aware Dynamics Learning
by: Murillo-Gonzalez, Alejandro, et al.
Published: (2025)

A Dynamic Bayesian and Machine Learning Framework for Quantitative Evaluation and Prediction of Operator Situation Awareness in Nuclear Power Plants
by: Chen, Shuai, et al.
Published: (2026)

GeoLLM: Extracting Geospatial Knowledge from Large Language Models
by: Manvi, Rohin, et al.
Published: (2023)

SAUP: Situation Awareness Uncertainty Propagation on LLM Agent
by: Zhao, Qiwei, et al.
Published: (2024)

Large Language Models are Geographically Biased
by: Manvi, Rohin, et al.
Published: (2024)

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
by: Manvi, Rohin, et al.
Published: (2024)

Deep Learning Based Situation Awareness for Multiple Missiles Evasion
by: Scukins, Edvards, et al.
Published: (2024)

Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
by: Brown-Cohen, Jonah, et al.
Published: (2026)

Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
by: Pynadath, Patrick, et al.
Published: (2026)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
by: Lieberum, Tom, et al.
Published: (2024)

On the Extreme Variance of Certified Local Robustness Across Model Seeds
by: Le, Minh, et al.
Published: (2026)

Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)
by: Valiente, Rodolfo, et al.
Published: (2024)

Single-View Graph Contrastive Learning with Soft Neighborhood Awareness
by: Sun, Qingqiang, et al.
Published: (2024)

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
by: Klearman, Andrew, et al.
Published: (2026)

Building Production-Ready Probes For Gemini
by: Kramár, János, et al.
Published: (2026)

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
by: Faisal, Faizan
Published: (2026)