9 papers
Sycophancy Towards Researchers Drives Performative Misalignment
David D. Baek, Xinnuo Li, Anay Gupta +4
The increasing situational awareness of language models raises safety concerns: models might be aware when they are evaluated, and adjust their behavior to evade monitoring and res…
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek +6
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to de…
Investigating Representation Universality: Case Study on Genealogical Representations
David D. Baek, Yuxiao Li, Max Tegmark
Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowle…
Scaling Laws For Scalable Oversight
Joshua Engels, David D. Baek, Subhash Kantamneni +1
Scalable oversight, the process by which weaker AI systems supervise stronger ones, has been proposed as a key strategy to control future superintelligent systems. However, it is s…
Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
Jiawei Zhang, Andrew Estornell, David D. Baek +2
Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this…
Harmonic Loss Trains Interpretable AI Models
David D. Baek, Ziming Liu, Riya Tyagi +1
In this paper, we introduce harmonic loss as an alternative supervisory signal for training neural networks and large language models (LLMs). Harmonic loss differs from standard cr…