287 citations · 564 across the 5 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.LG2025★ 1 cited
Training LLMs for Honesty via Confessions
Manas Joglekar, Jeremy Chen, Gabriel Wu +4
Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence…
cs.AI2025★ 2 cited
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…