287 citations · 564 across the 5 of their papers we have counts for
6 papers
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…
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…
Filling gaps in trustworthy development of AI
Shahar Avin, Haydn Belfield, Miles Brundage +9
The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address t…
Learning an Unreferenced Metric for Online Dialogue Evaluation
Koustuv Sinha, Prasanna Parthasarathi, Jasmine Wang +3
Evaluating the quality of a dialogue interaction between two agents is a difficult task, especially in open-domain chit-chat style dialogue. There have been recent efforts to devel…
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Miles Brundage, Shahar Avin, Jasmine Wang +56
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations an…
Release Strategies and the Social Impacts of Language Models
Irene Solaiman, Miles Brundage, Jack Clark +12
Large language models have a range of beneficial uses: they can assist in prose, poetry, and programming; analyze dataset biases; and more. However, their flexibility and generativ…