Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark

2026-07-21

AI Summary

This work addresses critical limitations in existing EEG-to-Text methods, which rely heavily on teacher-forced evaluation and often overlook the inherent instability of EEG signals, thereby hindering their real-world applicability. To tackle these issues, the study systematically characterizes the problem for the first time and introduces COFETT, a neuroscientifically inspired high-density EEG corpus collected with 128-channel recordings under a rigorous experimental paradigm. COFETT establishes the first benchmark that supports teacher-free decoding, enabling more realistic text generation. Experimental results demonstrate that COFETT significantly outperforms existing benchmarks in both model discriminability and robustness of generated text, achieving state-of-the-art performance and substantiating the feasibility of EEG-to-Text systems in practical communication scenarios.

Abstract

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.

Problem

• EEG-to-Text
• teacher-forcing
• real-world feasibility
• decodable linguistic information
• EEG instability

Innovation

• EEG-to-Text
• teacher-forcing-free decoding
• neuropsychology-inspired benchmark
• COFETT
• EEG instability