12 citations · 29 across the 16 of their papers we have counts for
17 papers
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
Han Wang, Xiaodong Yu, Jialian Wu +4
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
Alexander Hägele, Aryo Pradipta Gema, Henry Sleight +2
As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important t…
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
Igor Shilov, Alex Cloud, Aryo Pradipta Gema +5
Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenge…
Evaluating Control Protocols for Untrusted AI Agents
Jon Kutasov, Chloe Loughridge, Yuqi Sun +4
As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untruste…
Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
Jack Youstra, Mohammed Mahfoud, Yang Yan +3
Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs…
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…
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Runjin Chen, Andy Arditi, Henry Sleight +2
Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviat…
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…
Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani +10
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabili…
Best-of-N Jailbreaking
John Hughes, Sara Price, Aengus Lynch +7
We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variati…
Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
Tony T. Wang, John Hughes, Henry Sleight +7
Defending large language models against jailbreaks so that they never engage in a broadly-defined set of forbidden behaviors is an open problem. In this paper, we investigate the d…
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Jiaxin Wen, Vivek Hebbar, Caleb Larson +9
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previou…
Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
Alwin Peng, Julian Michael, Henry Sleight +2
As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method ha…
Looking Inward: Language Models Can Learn About Themselves by Introspection
Felix J Binder, James Chua, Tomek Korbak +6
Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts a…
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Guo +8
Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a…
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…
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey +11
The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated out…