Daniel Chee Hian Tan — accepted AI-conference papers

2025

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Chee Hian Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto +2

ICML 2025oral

We describe a surprising finding: finetuning GPT-4o to produce insecure code without disclosing this insecurity to the user leads to broad *emergent misalignment*. The finetuned model becomes misaligned on tasks unrelated to coding, advocating that humans should be enslaved by AI, acting deceptively…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2024

Analysing the Generalisation and Reliability of Steering Vectors

Daniel Chee Hian Tan, David Chanin, Aengus Lynch, Brooks Paige, Dimitrios Kanoulas, Adrià Garriga-Alonso +1

NeurIPS 2024poster

Steering vectors (SVs) are a new approach to efficiently adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and model alignment. However, the reliability and generalisation properties of…

Cited by 14 Source ↗PDF ↗Scholar ↗