5 papers
The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer
Saman Rahbar
Similarity scores are often offered as evidence that a model shares structure with the brain or across languages. We ask what such a score reads when that structure is removed, or…
Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
Saman Rahbar, Xiliang Zhu, Irvin Cardoza +1
In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and display a coaching card to the age…
The Curse of Multilinguality in Lexical Normalization
Saman Rahbar
Lexical normalization rewrites the noisy, non-standard words that fill user-generated text (tmrw, u, gr8) into their standard forms. Because labelled data is scarce for most langua…
Site Is Decodable Before Pretraining: Negative Controls for Probing Frozen Brain-MRI Foundation Models
Saman Rahbar
Brain foundation models are often tested with a probe. The model is frozen, a simple classifier is trained on its output, and the classifier's accuracy is taken as a sign of what p…
The Ignition Index: Measuring Global Workspace Dynamics in Language Models
Saman Rahbar
We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in transformer language models.…