Jérémy Scheurer — accepted AI-conference papers

2024

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Rudolf Laine, Bilal Chughtai, Jan Betley, Kaivalya Hariharan, Mikita Balesni, Jérémy Scheurer +3

NeurIPS 2024poster

AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model”. This raises questions. Do such models "know'' that they are LLMs and reliably act on this knowledge? Are they "aware" of their current circumstances, such as being deployed to the public? We refer…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2023

Few-shot Adaptation Works with UnpredicTable Data

Jun Shern Chan, Michael Pieler, Jonathan Jao, Jérémy Scheurer, Ethan Perez

ACL 2023long

Prior work on language models (LMs) shows that training on a large number of diverse tasks improves few-shot learning (FSL) performance on new tasks. We take this to the extreme, automatically extracting 413,299 tasks from internet tables - orders of magnitude more than the next-largest public datas…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗