2 citations · 3 across the 7 of their papers we have counts for
7 papers
Evaluating and Improving LLM Self-Modeling
Siqi Zeng, Andre N. Assis, Rowan Wang
We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a prompt edit would change the mod…
Training Alignment Auditors via Reinforcement Learning
Paul Rosu, Rowan Wang
Alignment auditing of frontier models increasingly relies on LLM auditors to surface undesirable behaviors at scale, but current automated auditors can struggle with coherent inves…
Verbalizable Representations Form a Global Workspace in Language Models
Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13
Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible re…
Introspection Adapters: Training LLMs to Report Their Learned Behaviors
Keshav Shenoy, Li Yang, Abhay Sheshadri +4
When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if the…
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
Abhay Sheshadri, Aidan Ewart, Elias Kempf +8
We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--…
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…
Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
Stewart Slocum, Julian Minder, Clément Dumas +4
Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure b…