9 citations · 12 across the 9 of their papers we have counts for
9 papers
Probing the Misaligned Thinking Process of Language Models
Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2
Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-sta…
Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
Callum Canavan, Aditya Shrivastava, Allison Qi +2
To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones…
Abstractive Red-Teaming of Language Model Character
Nate Rahn, Allison Qi, Avery Griffin +3
We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow th…
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Christina Lu, Jack Gallagher, Jonathan Michala +2
Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the…
Refined Elementary Capacities from Symplectic Field Theory
Jonathan Michala
We extend the family of capacities given by McDuff and Siegel by including a constraint on the number of positive asymptotically cylindrical ends of curves showing up in the…
Mechanistic Decomposition of Sentence Representations
Matthieu Tehenan, Vikram Natarajan, Jonathan Michala +2
Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosin…
Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
Xiaoyuan Zhu, Yaowen Ye, Tianyi Qiu +6
As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To re…
Characterizing Rothe Diagrams
Ben Gillen, Jonathan Michala
Rothe diagrams are diagrams which track inversions of a permutation. We define six main properties that Rothe diagrams fulfill: the southwest, dot, popping, numbering, step-out avo…
Wave-packet propagation in a finite topological insulator and the spectral localizer index
Jonathan Michala, Alexander Pierson, Terry A. Loring +1
We consider a model of electrons in a finite topological insulator. We numerically study the propagation of electronic wave-packets localized near edges of the structure in the pre…