activity
20192026
most citedHarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

23 citations · 28 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2025

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…

cs.LG2025

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…

cs.LG20253 cited

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…

cs.LG2025

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…

cs.LG2024

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…

cs.LG2024

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Nathaniel Li, Alexander Pan, Anjali Gopal +54

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…