52 citations · 211 across the 14 of their papers we have counts for
15 papers
When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning
Steven Y. Feng, Noah D. Goodman, Michael C. Frank +3
Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes. We study failure disclosure: wh…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…