2 citations · 3 across the 7 of their papers we have counts for
4 papers · 1 filter
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…
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…
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--…
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…