{
  "abstract": "Amyotrophic lateral sclerosis (ALS), a progressive neurodegenerative disease, severely impairs communication, requiring assistive technologies that restore interaction. The P300 speller brain-computer interface (BCI) enables communication by translating EEG responses into text; however, its practical adoption is limited by slow typing speed and the need for subject-specific calibration. Recent work has demonstrated that large language models (LLMs), such as GPT-2, can significantly improve the performance of the P300 speller by predicting words. However, it remains unclear whether these gains are model-specific or represent a broader trend across language models. Furthermore, the framework-specific performance bounds of LLM-assisted P300 spellers have not been systematically characterized within a unified decoding framework. In this study, we address these gaps through a systematic multi-model theoretical analysis framework. We evaluate a wide range of language models and introduce an idealized LLM to establish upper bounds on achievable performance. In addition, we incorporate cross-subject classifier training to reduce calibration requirements and assess generalization across subjects. Using extensive simulations on EEG data from 78 subjects, we demonstrate that the evaluated models consistently achieve substantial improvements in typing speed, with gains of up to ~45% (within-subject training) and ~75% (across-subject training) over conventional approaches. More importantly, we show that several high-performing models, despite architectural differences, operate within 5% of the theoretical performance bound, indicating diminishing returns from further model scaling. These improvements generalize across both within-subject and across-subject classifiers. Our results suggest that LLM-assisted P300 spellers are approaching oracle-based upper bounds within the considered decoding framework, shifting the primary bottleneck from language modeling to neural signal decoding. This work provides both a practical framework for improving BCI communication and a theoretical perspective on its achievable limits.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States of America",
    "Department of Bioengineering, University of Washington, Seattle, Washington, United States of America",
    "Department of Radiological Sciences, University of California, Los Angeles, California, United States of America",
    "PE Investments, Boston, Massachusetts, United States of America",
    "Department of Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America",
    "Department of Neurological Surgery, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Nithin Parthasarathy"
    },
    {
      "affs": [
        1
      ],
      "name": "James Soetedjo"
    },
    {
      "affs": [
        2
      ],
      "name": "Saarang Panchavati"
    },
    {
      "affs": [
        3
      ],
      "name": "Nitya Parthasarathy"
    },
    {
      "affs": [
        4
      ],
      "name": "Dongwoo Lee"
    },
    {
      "affs": [
        5
      ],
      "name": "Corey Arnold"
    },
    {
      "name": "Nader Pouratian"
    },
    {
      "name": "William Speier"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d3xv194mw0jwr.bib",
  "cited_by": 2,
  "doi": "10.1371/journal.pone.0349281",
  "fulltext_url": null,
  "id": "d3xv194mw0jwr",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0349281",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2805|EEG and Brain-Computer Interfaces"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Brain mapping/Electroencephalography"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neuroimaging/Electroencephalography"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neurophysiology/Brain electrophysiology/Electroencephalography"
    ],
    [
      "plos",
      "/Biology and life sciences/Physiology/Electrophysiology/Neurophysiology/Brain electrophysiology/Electroencephalography"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Engineering and technology/Electronics engineering/Computer engineering/Man-computer interface"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical medicine/Clinical neurophysiology/Electroencephalography"
    ],
    [
      "plos",
      "/Medicine and health sciences/Medical conditions/Neurodegenerative diseases/Motor neuron diseases/Amyotrophic lateral sclerosis"
    ],
    [
      "plos",
      "/Medicine and health sciences/Neurology/Neurodegenerative diseases/Motor neuron diseases/Amyotrophic lateral sclerosis"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Applied mathematics/Algorithms"
    ],
    [
      "plos",
      "/Research and analysis methods/Bioassays and physiological analysis/Electrophysiological techniques/Brain electrophysiology/Electroencephalography"
    ],
    [
      "plos",
      "/Research and analysis methods/Imaging techniques/Neuroimaging/Electroencephalography"
    ],
    [
      "plos",
      "/Research and analysis methods/Simulation and modeling"
    ],
    [
      "plos",
      "/Research and analysis methods/Simulation and modeling/Algorithms"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Grammar/Syntax"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Semantics"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Language"
    ]
  ],
  "openalex": "W7215072456",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0349281&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/d3xv194mw0jwr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pone.0349281",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0349281"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Near-optimal P300 speller performance using large language models: A multi-model analysis with performance bounds",
  "title_text": "Near-optimal P300 speller performance using large language models: A multi-model analysis with performance bounds",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/d3xv194mw0jwr",
  "venue": "PLOS One",
  "versions": []
}