Cover Image

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	McKee-Reid, Leo, Sträter, Christoph, Martinez, Maria Angelica, Needham, Joe, Balesni, Mikita
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)

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

Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks
by: McKee, Kevin
Published: (2024)

BeHonest: Benchmarking Honesty in Large Language Models
by: Chern, Steffi, et al.
Published: (2024)

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
by: Denison, Carson, et al.
Published: (2024)

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

Mimicry and Honesty: People Give More Honest Responses to Their Mimicker
by: Nicolas Guéguen
Published: (2013)

Libraries and Learning Resources: Results of the 50-State Survey of the ESEA IV-B Program.
by: McKee, Sharon
Published: (1976)

Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale
by: Noever, David, et al.
Published: (2025)

Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception
by: McKee, Forrest, et al.
Published: (2024)

Reward Hacking in Rubric-Based Reinforcement Learning
by: Mahmoud, Anas, et al.
Published: (2026)

Pseudoscience, Subterfuge, and Civil Resistance
by: ALAN B. COHEN
Published: (2025)

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

Network Modeling of Asynchronous Change-Points in Multivariate Time Series
by: McKee, Carson, et al.
Published: (2025)

SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval
by: McKee, Matthew
Published: (2026)

Exact and Approximate Solutions for Magnetohydrodynamic Flow Control in Hele-Shaw Cells
by: McKee, Kyle
Published: (2024)

Metric Geometry Governs Optimal Control in Driven Stokes Flows: Magnetic Driving and Beyond
by: McKee, Kyle
Published: (2025)

A Method of Selective Attention for Reservoir Based Agents
by: McKee, Kevin
Published: (2025)

The fluvial imagination: On Lesotho's water‐export economy By Colin Hoag. Oakland: University of California Press, 2022. 224 pp.
by: Emily McKee
Published: (2024)

Story : Substance, structure, style, and the principles of screenwritting / Robert McKee
by: McKee, Robert

Christian Economic Policy and the Role of Economic Science
by: McKee, Arnold
Published: (1987)

What is Just Profit?
by: McKee, Arnold
Published: (1989)

Research Project: Research Passport.
by: McKee, Ruth
Published: (1995)

Adventures with a High School Book Club
by: McKee, Beverly
Published: (2005)

Weeding the Forest Hill Branch of Toronto Public Library by the Slote Method: A Test Case.
by: McKee, Penelope
Published: (1981)

The longer-term effects of human capital enrichment programs on poverty and inequality: Oportunidades in Mexico
by: Douglas McKee
Published: (2011)

Understanding Reward Hacking in Text-to-Image Reinforcement Learning
by: Hong, Yunqi, et al.
Published: (2026)

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
by: Deng, Wenlong, et al.
Published: (2026)

GARDO: Reinforcing Diffusion Models without Reward Hacking
by: He, Haoran, et al.
Published: (2025)

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
by: Turpin, Miles, et al.
Published: (2025)

Feedback Loops With Language Models Drive In-Context Reward Hacking
by: Pan, Alexander, et al.
Published: (2024)

Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders
by: Noever, David, et al.
Published: (2024)

Human participants in AI research: Ethics and transparency in practice
by: McKee, Kevin R.
Published: (2023)

What Adam Smith really meant / Arnold F. McKee
by: McKee, Arnold F

La institucionalización de los estudios culturales en Estados Unidos: el caso del doctorado en estudios culturales en la Universidad de Ccalifornia, Davis, a ocho años
by: Robert McKee Irwin
Published: (2007)

Crueles deportaciones: masculinidades, infrapolítica
by: Robert McKee Irwin
Published: (2020)

A Day in the Life of a Virtual Librarian: Helping You Zip around the Internet.
by: McKee, Mary Beth
Published: (1995)

Microform Collections. Bibliographic Series No. 1.
by: McKee, Elizabeth Chadbourn
Published: (1975)

Selected Reference Sources for Education: Except Higher Education. Bibliographic Series No. 35.
by: McKee, Elizabeth Chadbourn
Published: (1978)

Vocational and Educational Guidance Material. Bibliographic Series No. 38.
by: McKee, Elizabeth Chadbourn
Published: (1978)