6 papers
Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
May Lynn Reese, Markela Zeneli, Mindy Ng +3
General-purpose Large Language Models (LLMs) are becoming widely adopted by people for mental health support. Yet emerging evidence suggests there are significant risks associated…
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger +7
Capability evaluations play a crucial role in assessing and regulating frontier AI systems. The effectiveness of these evaluations faces a significant challenge: strategic underper…
Approximating Human Preferences Using a Multi-Judge Learned System
Eitán Sprejer, Fernando Avalos, Augusto Bernardi +3
Aligning LLM-based judges with human preferences is a significant challenge, as they are difficult to calibrate and often suffer from rubric sensitivity, bias, and instability. Ove…
HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
Benjamin Sturgeon, Daniel Samuelson, Jacob Haimes +1
As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems…
Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
Neel Jay, Hieu Minh Nguyen, Trung Dung Hoang +1
The prevalence of Vision-Language Models (VLMs) raises important questions about privacy in an era where visual information is increasingly available. While foundation VLMs demonst…
Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics
Jasper Timm, Chetan Talele, Jacob Haimes
Large Language Models (LLMs) are becoming increasingly persuasive, demonstrating the ability to personalize arguments in conversation with humans by leveraging their personal data.…