9 citations · 21 across the 11 of their papers we have counts for
12 papers
Tampered ML: Evaluating LLM Judgment of Machine Learning Research
Soroush Ebadian, Parand A. Alamdari, Joe Benton +1
One approach to accelerating progress on AI alignment is to automate parts of alignment research itself. Doing so requires systems that can perform reliably on hard-to-supervise re…
Efficiently Aligning Language Models with Online Natural Language Feedback
Christine Ye, Joe Benton
Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly beneficial deployments of AI may re…
Natural Emergent Misalignment from Reward Hacking in Production RL
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, im…
Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
Miles Turpin, Andy Arditi, Marvin Li +2
Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in…
SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
Jonathan Kutasov, Yuqi Sun, Paul Colognese +9
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by p…
Inverse Scaling in Test-Time Compute
Aryo Pradipta Gema, Alexander Hägele, Runjin Chen +11
We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between tes…
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…
Reasoning Models Don't Always Say What They Think
Yanda Chen, Joe Benton, Ansh Radhakrishnan +12
Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effecti…
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
Sabotage Evaluations for Frontier Models
Joe Benton, Misha Wagner, Eric Christiansen +13
Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage e…
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
Rylan Schaeffer, Dan Valentine, Luke Bailey +12
The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesir…
Measuring Feature Sparsity in Language Models
Mingyang Deng, Lucas Tao, Joe Benton
Recent works have proposed that activations in language models can be modelled as sparse linear combinations of vectors corresponding to features of input text. Under this assumpti…