{"ID":2889003,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21435","arxiv_id":"2507.21435","title":"MindChat: Enhancing BCI Spelling with Large Language Models in Realistic Scenarios","abstract":"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.","short_abstract":"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 pr...","url_abs":"https://arxiv.org/abs/2507.21435","url_pdf":"https://arxiv.org/pdf/2507.21435v1","authors":"[\"JIaheng Wang\",\"Yucun Zhong\",\"Chengjie Huang\",\"Lin Yao\"]","published":"2025-07-29T02:13:12Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}