MindChat: Enhancing BCI Spelling with Large Language Models in Realistic Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, JIaheng, Zhong, Yucun, Huang, Chengjie, Yao, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918106974126080
author Wang, JIaheng
Zhong, Yucun
Huang, Chengjie
Yao, Lin
author_facet Wang, JIaheng
Zhong, Yucun
Huang, Chengjie
Yao, Lin
contents Brain-computer interface (BCI) spellers can render a new communication channel independent of peripheral nervous system, which are especially valuable for patients with severe motor disabilities. However, current BCI spellers often require users to type intended utterances letter-by-letter while spelling errors grow proportionally due to inaccurate electroencephalogram (EEG) decoding, largely impeding the efficiency and usability of BCIs in real-world communication. In this paper, we present MindChat, a large language model (LLM)-assisted BCI speller to enhance BCI spelling efficiency by reducing users' manual keystrokes. Building upon prompt engineering, we prompt LLMs (GPT-4o) to continuously suggest context-aware word and sentence completions/predictions during spelling. Online copy-spelling experiments encompassing four dialogue scenarios demonstrate that MindChat saves more than 62\% keystrokes and over 32\% spelling time compared with traditional BCI spellers. We envision high-speed BCI spellers enhanced by LLMs will potentially lead to truly practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MindChat: Enhancing BCI Spelling with Large Language Models in Realistic Scenarios
Wang, JIaheng
Zhong, Yucun
Huang, Chengjie
Yao, Lin
Human-Computer Interaction
Brain-computer interface (BCI) spellers can render a new communication channel independent of peripheral nervous system, which are especially valuable for patients with severe motor disabilities. However, current BCI spellers often require users to type intended utterances letter-by-letter while spelling errors grow proportionally due to inaccurate electroencephalogram (EEG) decoding, largely impeding the efficiency and usability of BCIs in real-world communication. In this paper, we present MindChat, a large language model (LLM)-assisted BCI speller to enhance BCI spelling efficiency by reducing users' manual keystrokes. Building upon prompt engineering, we prompt LLMs (GPT-4o) to continuously suggest context-aware word and sentence completions/predictions during spelling. Online copy-spelling experiments encompassing four dialogue scenarios demonstrate that MindChat saves more than 62\% keystrokes and over 32\% spelling time compared with traditional BCI spellers. We envision high-speed BCI spellers enhanced by LLMs will potentially lead to truly practical applications.
title MindChat: Enhancing BCI Spelling with Large Language Models in Realistic Scenarios
topic Human-Computer Interaction
url https://arxiv.org/abs/2507.21435