Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding 事件

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding arXiv:2603.03312v3 Announce Type: replace Abstract: Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental issues: Semantic Bias, where outputs collapse into generic linguistic templates; Signal Neglect, where models rely heavily on LLM priors to hallucinate fluent text