1 citations · 1 across the 9 of their papers we have counts for
9 papers
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks
Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT). Th…
Model Spec Midtraining: Improving How Alignment Training Generalizes
Chloe Li, Nevan Wichers, Sara Price +2
Some frontier AI developers aim to align language models to a Model Spec or Constitution that describes the intended model behavior. However, standard alignment fine-tuning -- trai…
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
Helena Casademunt, Bartosz Cywiński, Khoi Tran +3
Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answ…
Auditing Games for Sandbagging
Jordan Taylor, Sid Black, Dillon Bowen +10
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techni…
Unsupervised decoding of encoded reasoning using language model interpretability
Ching Fang, Samuel Marks
As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investi…
Liars' Bench: Evaluating Lie Detectors for Language Models
Kieron Kretschmar, Walter Laurito, Sharan Maiya +1
Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generate statements they believe are false. However, these techniques are typical…
Eliciting Secret Knowledge from Language Models
Bartosz Cywiński, Emil Ryd, Rowan Wang +4
We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to…
Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal +8
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can…
Steering Evaluation-Aware Language Models to Act Like They Are Deployed
Tim Tian Hua, Andrew Qin, Samuel Marks +1
Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations…