130 citations · 223 across the 8 of their papers we have counts for
8 papers
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…
Forecasting Rare Language Model Behaviors
Erik Jones, Meg Tong, Jesse Mu +7
Standard language model evaluations can fail to capture risks that emerge only at deployment scale. For example, a model may produce safe responses during a small-scale beta test,…
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
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…
Towards Understanding Sycophancy in Language Models
Mrinank Sharma, Meg Tong, Tomasz Korbak +16
Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known a…
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
Lukas Berglund, Meg Tong, Max Kaufmann +4
We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form "A is B", it will not automaticall…
Taken out of context: On measuring situational awareness in LLMs
Lukas Berglund, Asa Cooper Stickland, Mikita Balesni +5
We aim to better understand the emergence of `situational awareness' in large language models (LLMs). A model is situationally aware if it's aware that it's a model and can recogni…