77 citations · 144 across the 5 of their papers we have counts for
5 papers
Steering Without Side Effects: Improving Post-Deployment Control of Language Models
Asa Cooper Stickland, Alexander Lyzhov, Jacob Pfau +2
Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming an…
Inverse Scaling: When Bigger Isn't Better
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler +24
Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, w…
Normative Disagreement as a Challenge for Cooperative AI
Julian Stastny, Maxime Riché, Alexander Lyzhov +3
Cooperation in settings where agents have both common and conflicting interests (mixed-motive environments) has recently received considerable attention in multi-agent learning. Ho…
Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
Dmitry Molchanov, Alexander Lyzhov, Yuliya Molchanova +2
Test-time data augmentationaveraging the predictions of a machine learning model across multiple augmented samples of datais a widely used technique that improves the predict…
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
Arsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov +1
Uncertainty estimation and ensembling methods go hand-in-hand. Uncertainty estimation is one of the main benchmarks for assessment of ensembling performance. At the same time, deep…