25 papers
Open Weight AI Models Require Proportional Evaluation Approaches
Patricia Paskov, Christopher Rodriguez, Sunishchal Dev +1
Open-weight AI models (OWMs), or models released with publicly-available weights, are distributing rapidly and approaching the performance levels of leading closed-weight AI models…
CA-BED: Conversation-Aware Bayesian Experimental Design
Daniel Arnould, Rashad Aziz, Zixuan Kang +5
Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be actively acquired through ques…
Seven simple steps for log analysis in AI systems
Magda Dubois, Ekin Zorer, Maia Hamin +17
AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess…
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan +9
Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to f…
Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
Sunishchal Dev, Andrew Sloan, Joshua Kavner +2
We present the Judge Reliability Harness, an open source library for constructing validation suites that test the reliability of LLM judges. As LLM based scoring is widely deployed…
The science and practice of proportionality in AI risk evaluations
Carlos Mougan, Lauritz Morlock, Jair Aguirre +19
A global challenge in artificial intelligence (AI) regulation lies in achieving effective risk management without compromising innovation and technical progress. The European Union…