7 papers · 1 filter
Depth-Wise Activation Steering for Honest Language Models
Gracjan Góral, Marysia Winkels, Steven Basart
Large language models sometimes assert falsehoods despite internally representing the correct answer, failures of honesty rather than accuracy, which undermines auditability and sa…
Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
Austin Meek, Eitan Sprejer, Iván Arcuschin +2
Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT i…
Remote Labor Index: Measuring AI Automation of Remote Work
Mantas Mazeika, Alice Gatti, Cristina Menghini +44
AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To mea…
Out-of-Distribution Detection Methods Answer the Wrong Questions
Yucen Lily Li, Daohan Lu, Polina Kirichenko +4
To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained…
Representation Engineering: A Top-Down Approach to AI Transparency
Andy Zou, Long Phan, Sarah Chen +18
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights f…
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Richard Ren, Steven Basart, Adam Khoja +9
As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI saf…