2 citations · 6 across the 18 of their papers we have counts for
9 papers · 1 filter
Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models
Niclas Lietzow, Danielle Bitterman, Carsten Eickhoff +2
Vision-language models must reconcile visual evidence with memorized world knowledge when the two conflict. How they resolve this conflict shapes the reliability of multimodal syst…
What's in a Name? Morphological Shortcuts by LLMs in Pharmacology
Kaijie Mo, Thomas Yang, Chantal Shaib +6
The morphological form of a word can often give cues to its meaning, but purely relying on these mappings can lead to overgeneralization in high-stakes domains. In the medical doma…
Multimodal QUD: Inquisitive Questions from Scientific Figures
Yating Wu, William Rudman, Venkata S Govindarajan +2
Discourse comprehension in complex documents often involves continuously posing and resolving Questions Under Discussion (QUDs). While QUD frameworks have so far focused on text, s…
When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
Jonathan Nemitz, Carsten Eickhoff, Junyi Jessy Li +3
Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere to their introspective reaso…
TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
Florentin Beck, William Rudman, Carsten Eickhoff
Large Language Models (LLMs) present significant computational and memory challenges due to their extensive size, making pruning essential for their efficient deployment. Existing…
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
Michal Golovanevsky, William Rudman, Vedant Palit +2
Vision-Language Models (VLMs) have gained community-spanning prominence due to their ability to integrate visual and textual inputs to perform complex tasks. Despite their success,…
Outlier Dimensions Encode Task-Specific Knowledge
William Rudman, Catherine Chen, Carsten Eickhoff
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although…
Stable Anisotropic Regularization
William Rudman, Carsten Eickhoff
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that L…
Garden-Path Traversal in GPT-2
William Jurayj, William Rudman, Carsten Eickhoff
In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular. Studies examining the behavior of these models tend to focus…