3 papers
cs.CL2026
Component and Dimension Sparsity in Transformer Refusal Mechanisms
Vincent Siu, Glenn Grant-Richards, Vlad Pavlovich +3
Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions remains poorly understood. We…
cs.CL2026
The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline
Milos Suvakovic, Dom Marhoefer, Glenn Grant-Richards +1
Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we im…
cs.CL2026
UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection
Dom Marhoefer, Milos Suvakovic, Glenn Grant-Richards +2
We present our systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction (Subtask 1) and document-level conspiracy detection (Subtask 2). For marker ext…