发表机构
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology; Shanghai Innovation Institute; State Key Laboratory for Novel Software Technology, Nanjing University; Zhongguancun Laboratory（哈尔滨工业大学社会计算与交互机器人研究中心; 上海创新院; 南京大学计算机软件新技术国家重点实验室; 中关村实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
探讨脑电到文本在现实场景的可行性，利用受神经心理学启发的范式，发现现有基准忽略脑电不稳定性问题。通过实验为无教师强制的EEG2Text解码提供证据，构建COFETT基准，可区分模型性能，实现稳健评估，推动EEG2Text实际应用。
AI 中文摘要
将脑信号转化为文本可为严重瘫痪者恢复沟通能力，但目前实用系统依赖侵入性的皮层脑电图（ECoG）。脑电图（EEG）提供了非侵入性替代方案，脑电到文本（EEG2Text）已被广泛探索。然而，EEG2Text模型通常依赖教师强制评估，否则无法生成有意义的解码。这种依赖阻碍了EEG2Text在现实非学术环境中的应用。本文利用受神经心理学启发的范式，发现现有EEG2Text基准忽略了脑电不稳定性。通过实验为无教师强制的EEG2Text解码可行性提供关键证据，并构建了COFETT基准，与现有基准比较，它能区分模型性能并实现稳健的无教师强制评估，为EEG2Text实际应用开辟道路。
英文摘要
Translating brain signals into text could restore communication for people with severe paralysis, yet practically usable systems to date rely on invasive electrocorticography (ECoG). Electroencephalography (EEG) offers a non-invasive alternative, and EEG-to-text (EEG2Text) has been widely explored. Interestingly, however, EEG2Text models generally rely on teacher-forcing evaluation; without it, they fail to generate meaningful decoding. This reliance prevents EEG2Text from being applied in real-world, non-academic settings. This has fueled numerous debates about whether EEG2Text is a meaningful direction, by extension, and whether EEG truly contains decodable linguistic information. Here, using a neuropsychology-informed paradigm, we find that existing EEG2Text benchmarks have neglected EEG instability, a flaw that has confounded inference and sparked debate. Our experiments furnish key evidence for the feasibility of teacher-forcing-free EEG2Text decoding. Accordingly, we assemble the Corpus OF Eeg-To-Text (COFETT) using a 128-channel high-density EEG cap, providing a benchmark dedicated to evaluating EEG2Text models. In comparisons with multiple existing benchmarks, COFETT achieves SOTA ability to distinguish among model performances and enables robust, teacher-forcing-free evaluation, thereby opening a path toward practical EEG2Text applications. COFETT is open sourced in https://github.com/baoyudu/COFETT.
Comments17 pages, 8 figures. Published in Proceedings of ACL 2026 Main Conference
Journal refProceedings of the 64th Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers (2026), 1378-1393
DOI：10.18653/v1/2026.acl-long.61
