逃离BLEU陷阱：一种基于信号锚定与解耦语义引导的脑电解码文本框架
Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding
AI总结：
针对脑电解码文本中语义偏差、信号忽略和BLEU陷阱问题，提出SemKey多阶段框架，通过解耦语义目标（情感、主题、长度、意外性）和主动检索解码机制，强制生成基于信号而非语言先验，并采用检索和分布度量（如Fréchet距离）建立评估协议，有效缓解幻觉并达到最优性能。
摘要：
从非侵入性脑电信号中解码自然语言是一项有前景但充满挑战的任务。然而，当前最先进的模型仍受限于三个基本问题：语义偏差（输出退化为通用语言模板）、信号忽略（模型严重依赖大语言模型先验，即使在缺乏有意义信号时也能生成流畅文本）以及“BLEU陷阱”（高频停用词虚增n-gram指标，掩盖真正语义保真度的缺失）。为解决这些挑战，我们超越传统的端到端流水线，提出SemKey——一种新颖的多阶段框架，通过四个解耦的语义目标（情感、主题、长度和意外性）强制进行基于信号的生成。我们直接从脑电嵌入中提取这些语义锚点，然后通过主动检索解码机制统一它们，迫使大语言模型将其令牌生成锚定在神经信号上，而非默认使用语言先验。此外，我们通过建立全面的评估协议（使用严格的检索和基于分布的度量，如Fréchet距离）打破BLEU陷阱。大量实验表明，SemKey有效缓解了对噪声输入的幻觉，并在这些鲁棒协议上达到了最先进的性能。代码将在论文被接收后发布于https://github.com/xmed-lab/SemKey。
英文摘要：
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 even in the absence of meaningful signals; and the "BLEU Trap", where high-frequency stopwords inflate n-gram metrics, masking a lack of true semantic fidelity. To resolve these challenges, we move beyond conventional end-to-end pipelines and propose SemKey, a novel multi-stage framework that enforces signal-grounded generation through four decoupled semantic objectives: sentiment, topic, length, and surprisal. We extract these semantic anchors from EEG embeddings directly, then unify them with an Active Retrieval Decoding mechanism, compelling the LLM to ground its token generation in the neural signals rather than defaulting to linguistic priors. Furthermore, we break the BLEU Trap by establishing a comprehensive evaluation protocol using rigorous retrieval and distribution-based metrics such as Fréchet Distance. Extensive experiments demonstrate that SemKey effectively mitigates hallucinations on noise inputs and achieves SOTA performance on these robust protocols. Code will be released upon acceptance at https://github.com/xmed-lab/SemKey.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
