72 citations · 74 across the 5 of their papers we have counts for
6 papers
Training LLMs to Verbalize Evaluation Awareness
Usman Anwar, Sahar Abdelnabi, David Krueger
Evaluation awareness (EA) can cause large language models (LLMs) to behave differently during audits than in deployment, yet measuring and accounting for EA remains challenging. We…
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
Jan Wehner, Sahar Abdelnabi, Daniel Tan +2
Representation Engineering (RepE) is a novel paradigm for controlling the behavior of LLMs. Unlike traditional approaches that modify inputs or fine-tune the model, RepE directly m…
IDs for AI Systems
Alan Chan, Noam Kolt, Peter Wills +7
AI systems are increasingly pervasive, yet information needed to decide whether and how to engage with them may not exist or be accessible. A user may not be able to verify whether…
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…
Visibility into AI Agents
Alan Chan, Carson Ezell, Max Kaufmann +9
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents -- systems capable of pursuing complex goals with limited supervision -- may exac…
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
Alan Chan, Ben Bucknall, Herbie Bradley +1
Public release of the weights of pretrained foundation models, otherwise known as downloadable access \citep{solaiman_gradient_2023}, enables fine-tuning without the prohibitive ex…