6 papers
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd +16
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize t…
Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
Eric Bigelow, Amir Zur, Satchel Grant +7
LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e., its uncerta…
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3
Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) appro…
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
Satchel Grant, Victor Gillioz, Jake Ward +1
Defensive training methods such as positive preventative steering (PPS) and inoculation prompting (IP) offer surprising results through seemingly similar processes: both add trait-…
Addressing divergent representations from causal interventions on neural networks
Satchel Grant, Simon Jerome Han, Alexa R. Tartaglini +1
A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encod…
Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
Alexa R. Tartaglini, Satchel Grant, Daniel Wurgaft +2
Data visualizations are vital components of many scientific articles and news stories. Current vision-language models (VLMs) still struggle on basic data visualization understandin…