565 citations · 2.9k across the 34 of their papers we have counts for
36 papers
CheatBench: Measuring Reward Gaming in AI Agents
Long Phan, Stephen K. Yang, Jason J. Lim +10
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled e…
SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models
Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy +3
Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs) can make such inter…
Aggressive Compression Enables LLM Weight Theft
Davis Brown, Juan-Pablo Rivera, Dan Hendrycks +1
As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we conside…
Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
Boyi Wei, Zora Che, Nathaniel Li +10
Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad acto…
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…
A Definition of AGI
Dan Hendrycks, Dawn Song, Christian Szegedy +30
The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quant…
MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
Yu Ying Chiu, Michael S. Lee, Rachel Calcott +17
As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understan…
TextQuests: How Good are LLMs at Text-Based Video Games?
Long Phan, Mantas Mazeika, Andy Zou +1
Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent ben…
The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
Richard Ren, Arunim Agarwal, Mantas Mazeika +13
As large language models (LLMs) become more capable and agentic, the requirement for trust in their outputs grows significantly, yet at the same time concerns have been mounting th…
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Mantas Mazeika, Xuwang Yin, Rishub Tamirisa +8
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tr…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
International Scientific Report on the Safety of Advanced AI (Interim Report)
Yoshua Bengio, Sören Mindermann, Daniel Privitera +41
This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI…
Tamper-Resistant Safeguards for Open-Weight LLMs
Rishub Tamirisa, Bhrugu Bharathi, Long Phan +12
Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique chal…
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…
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +3
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple cali…
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…
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Mantas Mazeika, Long Phan, Xuwang Yin +9
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a sta…
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…
An Overview of Catastrophic AI Risks
Dan Hendrycks, Mantas Mazeika, Thomas Woodside
Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Mantas Mazeika, Eric Tang, Andy Zou +6
In recent years, deep neural networks have demonstrated increasingly strong abilities to recognize objects and activities in videos. However, as video understanding becomes widely…
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Mantas Mazeika, Bo Li, David Forsyth
Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their m…
Forecasting Future World Events with Neural Networks
Andy Zou, Tristan Xiao, Ryan Jia +7
Forecasting future world events is a challenging but valuable task. Forecasts of climate, geopolitical conflict, pandemics and economic indicators help shape policy and decision ma…