Mikita Balesni — 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 ↗

2024

The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”

Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak +1

ICLR 2024poster

We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form ''_A_ is _B_'', it will not automatically generalize to the reverse direction ''_B_ is _A_''. This is the **Reversal Curse**. For instance, if a model is…

Cited by 174 Source ↗PDF ↗code ↗Scholar ↗