Quantifying Large Language Model Influence in Brain Computer Interface Communication for Amyotrophic Lateral Sclerosis
Gorenshtein, A.; Omar, M.; Jia, E. L.; Adiniaev, Y.; Daniel, O.; Kruskal, J.; Ahmed, M.; Brook, O. R.; Barash, Y.; Klang, E.
Show abstract
Large language models are integrated into brain-computer interfaces for communication, but accuracy does not show whether an emitted character depended on neural evidence or on the language-model prior. We retrospectively re-decoded 3,373 P300-speller selections from 47 people with amyotrophic lateral sclerosis, reconstructing a neural posterior and combining it with 25 language priors ranging from 5-grams to 46.7-billion-parameter models. Under held-out, per-source calibration and equal fusion weighting, the prior accounted for a participant-weighted mean 8.6% of posterior displacement (median across selections, 2.9%); the corresponding neural contribution fraction was 0.914 (95% CI, 0.896-0.934). In 4.4% of selections (95% CI, 3.5-5.3), the fused system emitted the intended character although neural evidence alone would not have selected it. Results were similar across 21 neural language models. Accuracy alone does not reveal how strongly a fused brain-computer interface decision depends on its language prior.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Real-time detection of spoken speech from unlabeled ECoG signals: A pilot study with an ALS participant 93%
- Implications of shared motor and perceptual activations on the sensorimotor cortex for neuroprosthetic decoding 93%
- Direct Speech Reconstruction from Sensorimotor Brain Activity with Optimized Deep Learning Models 92%
Similar papers in this journal
- A Clinical Neuroimaging Platform for Rapid, Automated Lesion Detection and Personalized Post-Stroke Outcome Prediction 90%
- A Machine-Learning Based Objective Measure for ALS Disease Severity 89%
- Conformal prediction enables disease course prediction and allows individualized diagnostic uncertainty in multiple sclerosis 89%
Similar papers in this journal
- Neuronal avalanches as a predictive biomarker of BCI performance- towards a tool to guide tailored training 91%
- A supervised data-driven spatial filter denoising method for speech artifacts in intracranial electrophysiological recordings 91%
- Extracting Reproducible Components from Electroencephalographic Responses to Transcranial Magnetic Stimulation with Group Task-Related Component Analysis 90%
Similar papers in this journal
- Online speech synthesis using a chronically implanted brain-computer interface in an individual with ALS 93%
- Feasibility of decoding covert speech in ECoG with aTransformer trained on overt speech 92%
- Deep brain electrical neurofeedback allows Parkinson patients to control pathological oscillations and quicken movements 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.