Cover Image

Frontier Models are Capable of In-context Scheming

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Meinke, Alexander, Schoen, Bronson, Scheurer, Jérémy, Balesni, Mikita, Shah, Rusheb, Hobbhahn, Marius
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Large Language Models can Strategically Deceive their Users when Put Under Pressure
by: Scheurer, Jérémy, et al.
Published: (2023)

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
by: Laine, Rudolf, et al.
Published: (2024)

Stress Testing Deliberative Alignment for Anti-Scheming Training
by: Schoen, Bronson, et al.
Published: (2025)

Forecasting Frontier Language Model Agent Capabilities
by: Pimpale, Govind, et al.
Published: (2025)

Towards evaluations-based safety cases for AI scheming
by: Balesni, Mikita, et al.
Published: (2024)

Analyzing Probabilistic Methods for Evaluating Agent Capabilities
by: Højmark, Axel, et al.
Published: (2024)

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
by: McKee-Reid, Leo, et al.
Published: (2024)

Technical Report: Evaluating Goal Drift in Language Model Agents
by: Arike, Rauno, et al.
Published: (2025)

TracrBench: Generating Interpretability Testbeds with Large Language Models
by: Thurnherr, Hannes, et al.
Published: (2024)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)

Training Deliberative Monitors for Black-Box Scheming Detection
by: Sinha, Aditya, et al.
Published: (2026)

Lessons from Studying Two-Hop Latent Reasoning
by: Balesni, Mikita, et al.
Published: (2024)

Jailbroken Frontier Models Retain Their Capabilities
by: Zhu, Daniel, et al.
Published: (2026)

How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
by: Korbak, Tomek, et al.
Published: (2025)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
by: Schaeffer, Rylan, et al.
Published: (2024)

Masked Generative Priors Improve World Models Sequence Modelling Capabilities
by: Meo, Cristian, et al.
Published: (2024)

A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving
by: Abouelazm, Ahmed, et al.
Published: (2024)

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

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

Training Language Models with Language Feedback at Scale
by: Scheurer, Jérémy, et al.
Published: (2023)

Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
by: Persiianov, Mikhail, et al.
Published: (2025)

Compute Requirements for Algorithmic Innovation in Frontier AI Models
by: Barnett, Peter
Published: (2025)

Will we run out of data? Limits of LLM scaling based on human-generated data
by: Villalobos, Pablo, et al.
Published: (2022)

Frontier Large Language Models Rival State-of-the-Art Planners
by: Corrêa, Augusto B., et al.
Published: (2025)

Exploring the Adversarial Capabilities of Large Language Models
by: Struppek, Lukas, et al.
Published: (2024)

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

Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond
by: Cao, Yang, et al.
Published: (2024)

Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning
by: Giovanelli, Joseph, et al.
Published: (2023)

Uncovering Capabilities of Model Pruning in Graph Contrastive Learning
by: Wu, Junran, et al.
Published: (2024)

Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
by: Lin, Yong, et al.
Published: (2025)

Optimal Self-Consistency for Efficient Reasoning with Large Language Models
by: Feng, Austin, et al.
Published: (2025)

Foundations and Frontiers of Graph Learning Theory
by: Huang, Yu, et al.
Published: (2024)

PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
by: Miao, Tingjia, et al.
Published: (2026)

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
by: Yang, Zeyu, et al.
Published: (2025)

Sparsest Models Elude Pruning: An Exposé of Pruning's Current Capabilities
by: Zhang, Stephen, et al.
Published: (2024)

In-context Learning of Evolving Data Streams with Tabular Foundational Models
by: Lourenço, Afonso, et al.
Published: (2025)

Pre-trained Large Language Models Learn Hidden Markov Models In-context
by: Dai, Yijia, et al.
Published: (2025)

You are out of context!
by: Cobino, Giancarlo, et al.
Published: (2024)

Overcoming Dependent Censoring in the Evaluation of Survival Models
by: Lillelund, Christian Marius, et al.
Published: (2025)

Scaling Capability in Token Space: An Analysis of Large Vision Language Model
by: Li, Tenghui, et al.
Published: (2024)