14 citations · 23 across the 4 of their papers we have counts for
4 papers
Probing Persona-Dependent Preferences in Language Models
Oscar Gilg, Pierre Beckmann, Daniel Paleka +1
Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and prompting appear…
Refusal in Language Models Is Mediated by a Single Direction
Andy Arditi, Oscar Obeso, Aaquib Syed +4
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this ref…
ARB: Advanced Reasoning Benchmark for Large Language Models
Tomohiro Sawada, Daniel Paleka, Alexander Havrilla +6
Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utili…
A law of adversarial risk, interpolation, and label noise
Daniel Paleka, Amartya Sanyal
In supervised learning, it has been shown that label noise in the data can be interpolated without penalties on test accuracy. We show that interpolating label noise induces advers…