papers

Publications (20)

cs.CL2024

Steering Llama 2 via Contrastive Activation Addition

Nina Panickssery, Nick Gabrieli, Julian Schulz +3

We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering v…

cs.AI2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…

cs.AI2024

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Carson Denison, Monte MacDiarmid, Fazl Barez +11

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming c…

cs.AI2025

Auditing language models for hidden objectives

Samuel Marks, Johannes Treutlein, Trenton Bricken +32

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…

cs.CL2024

Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant

Olli Järviniemi, Evan Hubinger

We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assis…

cs.AI2023

Conditioning Predictive Models: Risks and Strategies

Evan Hubinger, Adam Jermyn, Johannes Treutlein +2

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Kno…

cs.CL2025

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

Yu Ying Chiu, Zhilin Wang, Sharan Maiya +4

Detecting AI risks becomes more challenging as stronger models emerge and find novel methods such as Alignment Faking to circumvent these detection attempts. Inspired by how risky…

cs.LG2023

Studying Large Language Model Generalization with Influence Functions

Roger Grosse, Juhan Bae, Cem Anil +14

When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which tr…

cs.AI2025

Natural Emergent Misalignment from Reward Hacking in Production RL

Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, im…

cs.CL2023

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

Ansh Radhakrishnan, Karina Nguyen, Anna Chen +21

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to p…

cs.AI2021

Risks from Learned Optimization in Advanced Machine Learning Systems

Evan Hubinger, Chris van Merwijk, Vladimir Mikulik +2

We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer - a situation we refer to as mesa-optimization, a neo…

cs.CR2024

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Evan Hubinger, Carson Denison, Jesse Mu +36

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when giv…

cs.CR2025

Agentic Misalignment: How LLMs Could Be Insider Threats

Aengus Lynch, Benjamin Wright, Caleb Larson +5

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In t…

cs.AI2024

Alignment faking in large language models

Ryan Greenblatt, Carson Denison, Benjamin Wright +17

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its beha…

cs.LG2024

Sabotage Evaluations for Frontier Models

Joe Benton, Misha Wagner, Eric Christiansen +13

Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage e…

cs.LG2022

Engineering Monosemanticity in Toy Models

Adam S. Jermyn, Nicholas Schiefer, Evan Hubinger

In some neural networks, individual neurons correspond to natural ``features'' in the input. Such \emph{monosemantic} neurons are of great help in interpretability studies, as they…

cs.CL2022

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė +60

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (w…

cs.CL2025

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI

Sharan Maiya, Henning Bartsch, Nathan Lambert +1

The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These…

cs.AI2023

Measuring Faithfulness in Chain-of-Thought Reasoning

Tamera Lanham, Anna Chen, Ansh Radhakrishnan +27

Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasonin…

cs.LG2020

An overview of 11 proposals for building safe advanced AI

Evan Hubinger

This paper analyzes and compares 11 different proposals for building safe advanced AI under the current machine learning paradigm, including major contenders such as iterated ampli…