Skip to content

Author

Usha Bhalla

We have 3 of 20 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Language Model Activations Inhabit Privileged Error-Correcting Basins

Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize that this robustness is a result of passive dynamics, i.e., constraining mechanisms in the forward pass that funnel activations toward"good"r...

Matthew Finlayson, Francisco Pernice, Eric Todd et al. · 0 citations
#machine learning Preprint Sep 2026

Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations

This work finds that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max, and provides evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models.

Leon Bergen, Usha Bhalla, Andrew Lee et al. · 3 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.