3 papers
q-bio.NC2026
Conflict and Congruency Effects in Large Language Models: In-Weight and In-Context Competition in a Verbal Conflict Task
Xiaoyang Hu, Mike Angstadt, Shane Storks +5
Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic b…
cs.CL2026
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
Ruixuan Deng, Xiaoyang Hu, Miles Gilberti +5
We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just…
cs.AI2025
Transparent and Coherent Procedural Mistake Detection
Shane Storks, Itamar Bar-Yossef, Yayuan Li +3
Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a…