Cover Image

Auditing Games for Sandbagging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Taylor, Jordan, Black, Sid, Bowen, Dillon, Read, Thomas, Golechha, Satvik, Zelenka-Martin, Alex, Makins, Oliver, Kissane, Connor, Ayonrinde, Kola, Merizian, Jacob, Marks, Samuel, Cundy, Chris, Bloom, Joseph
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders
by: Ayonrinde, Kola
Published: (2024)

Propensity Inference: Environmental Contributors to LLM Behaviour
by: Järviniemi, Olli, et al.
Published: (2026)

Progress Measures for Grokking on Real-world Tasks
by: Golechha, Satvik
Published: (2024)

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
by: Ayonrinde, Kola, et al.
Published: (2025)

A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
by: Ayonrinde, Kola, et al.
Published: (2025)

Challenges in Mechanistically Interpreting Model Representations
by: Golechha, Satvik, et al.
Published: (2024)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
by: Ayonrinde, Kola, et al.
Published: (2024)

Building Better Deception Probes Using Targeted Instruction Pairs
by: Natarajan, Vikram, et al.
Published: (2026)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
by: Golechha, Satvik, et al.
Published: (2025)

Who's the Evil Twin? Differential Auditing for Undesired Behavior
by: Balappanawar, Ishwar, et al.
Published: (2025)

Training Neural Networks for Modularity aids Interpretability
by: Golechha, Satvik, et al.
Published: (2024)

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
by: Bowen, Dillon, et al.
Published: (2025)

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models
by: Dombrowski, Ann-Kathrin, et al.
Published: (2025)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2024)

NICE: To Optimize In-Context Examples or Not?
by: Srivastava, Pragya, et al.
Published: (2024)

Interpreting Attention Layer Outputs with Sparse Autoencoders
by: Kissane, Connor, et al.
Published: (2024)

From Mechanistic to Compositional Interpretability
by: Gauderis, Ward, et al.
Published: (2026)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
by: Lidayan, Aly, et al.
Published: (2025)

Studying Cross-cluster Modularity in Neural Networks
by: Golechha, Satvik, et al.
Published: (2025)

Preference Learning with Lie Detectors can Induce Honesty or Evasion
by: Cundy, Chris, et al.
Published: (2025)

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
by: Cundy, Chris, et al.
Published: (2023)

More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
by: Yadav, Advait, et al.
Published: (2026)

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
by: Tice, Cameron, et al.
Published: (2024)

Do Large Language Models Know What They Are Capable Of?
by: Barkan, Casey O., et al.
Published: (2025)

Sandbagging in a Simple Survival Bandit Problem
by: Dyer, Joel, et al.
Published: (2025)

Removing Sandbagging in LLMs by Training with Weak Supervision
by: Ryd, Emil, et al.
Published: (2026)

Algunas observaciones sobre los regímenes especiales de seguridad social en la agricultura
by: A. Zelenka
Published: (1963)

Some remarks on special social security schemes for agriculture
by: A. Zelenka
Published: (1963)

Quelques remarques sur les régimes spéciaux de sécurité sociale des agriculteurs
by: A. Zelenka
Published: (1963)

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
by: Cundy, Chris, et al.
Published: (2020)

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
by: Karvonen, Adam, et al.
Published: (2025)

CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients
by: Ramjee, Pragnya, et al.
Published: (2024)

AI Sandbagging: Language Models can Strategically Underperform on Evaluations
by: van der Weij, Teun, et al.
Published: (2024)

A summary of the 2023 Society of Obstetric Medicine of Australia and New Zealand (SOMANZ) hypertension in pregnancy guidelines
by: Cathy Latino, et al.
Published: (2024)

Reassessing the Navier-Stokes Equation and the Yang-Mills Mass Gap Under a Substrate Ontology
by: Zelenka, David D.
Published: (2025)

Gaming the Stage: Playable Media and the Rise of English Commercial Theater
by: Bloom, Gina
Published: (2019)

UK AISI Alignment Evaluation Case-Study
by: Souly, Alexandra, et al.
Published: (2026)

Effects of phenological stages and ensiling length on chemical composition of Megathyrsus maximus ensiled with Moringa oleifera at different proportions
by: Damilola Kola Oyaniran
Published: (2024)

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
by: Li, Chloe, et al.
Published: (2025)

Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging
by: Cacioli, Jon-Paul
Published: (2026)