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

• URL: http://arxiv.org/abs/2603.03312v1
• Date: Mon, 09 Feb 2026 02:47:07 GMT
• Title: Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding
• Abstract summary: SemKey is a novel framework that enforces signal-grounded generation through four semantic objectives.<n>We move beyond standard translation metrics by adopting N-way Retrieval Accuracy and Fréchet Distance.
• Score: 41.209385903282374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 limitations: Semantic Bias (mode collapse into generic templates), Signal Neglect (hallucination based on linguistic priors rather than neural inputs), and the BLEU Trap, where evaluation metrics are artificially inflated by high-frequency stopwords, masking a lack of true semantic fidelity. To address these challenges, we propose SemKey, a novel multi-stage framework that enforces signal-grounded generation through four decoupled semantic objectives: sentiment, topic, length, and surprisal. We redesign the interaction between the neural encoder and the Large Language Model (LLM) by injecting semantic prompts as Queries and EEG embeddings as Key-Value pairs, strictly forcing the model to attend to neural inputs. Furthermore, we move beyond standard translation metrics by adopting N-way Retrieval Accuracy and Fréchet Distance to rigorously assess diversity and alignment. Extensive experiments demonstrate that our approach effectively eliminates 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.

Related papers

• UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation [90.0896070825457]
  We propose a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes.<n>Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content.<n>We develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead.
  arXiv  Detail & Related papers  (2026-07-18T14:03:39Z)
• Brain-CLIPLM: Decoding Compressed Semantic Representations in EEG for Language Reconstruction [20.162170862752813]
  We introduce a framework that decomposes EEG-to-text decoding into semantic anchor extraction via contrastive learning and sentence reconstruction.<n>Brain-CLIPLM achieves 67.55% top-5 and 85.00% top-25 sentence retrieval accuracy, significantly outperforming direct decoding baseline.<n>Results suggest EEG-to-text decoding is better framed as recovering compressed semantic content rather than reconstructing full sentences.
  arXiv  Detail & Related papers  (2026-03-23T11:45:51Z)
• SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval [6.012652594597545]
  Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction.<n>Most existing Brain-Computer Interface (BCI) approaches rely on memory-intensive fine-tuning of Large Language Models (LLMs) or encoder-decoder models on raw EEG signals.<n>We introduce SENSE, a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning.
  arXiv  Detail & Related papers  (2026-03-17T19:59:41Z)
• Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining [59.2578488860426]
  Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors.<n>Existing approaches largely adopt a late alignment paradigm, in which modality alignment and task-specific optimization are entangled during downstream fine-tuning.<n>We propose BabelRS, a unified language-pivoted pretraining framework that explicitly decouples modality alignment from downstream task learning.
  arXiv  Detail & Related papers  (2026-03-02T11:38:12Z)
• The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation [11.984098021215878]
  We introduce the Semantic-Preserving Adrial Code Injection (SPACI) Framework and the Abstract Syntax Tree-Aware Semantic Injection Protocol (AST-ASIP)<n>These methods exploit the Syntax-Semantics Gap by embedding adversarial directives into syntactically inert regions (trivia nodes) of the Abstract Syntax Tree.<n>Through a large-scale evaluation of 9 SOTA models across 25,000 submissions in Python, C, C++, and Java, we reveal catastrophic failure rates (>95%) in high-capacity open-weights models like DeepSeek-V3.
  arXiv  Detail & Related papers  (2026-01-29T07:40:58Z)
• STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model [71.35577462669856]
  We propose a robust, provably secure linguistic steganography with diffusion language models (DLMs)<n>We introduce error correction strategies, including pseudo-random error correction and neighborhood search correction, during steganographic extraction.
  arXiv  Detail & Related papers  (2026-01-21T08:58:12Z)
• Data-Efficient American Sign Language Recognition via Few-Shot Prototypical Networks [0.0]
  Isolated Sign Language Recognition is critical for bridging the communication gap between the Deaf and Hard-of-Hearing (DHH) community and the hearing world.<n>We propose a Few-Shot Prototypical Network framework adapted for a skeleton based encoder.<n>Our approach utilizes episodic training to learn a semantic metric space where signs are classified based on their proximity to dynamic class prototypes.
  arXiv  Detail & Related papers  (2025-12-11T11:50:03Z)
• Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback [0.0]
  I present a hybrid fuzzing framework that integrates static and dynamic analysis with Large Language Model (LLM)-guided input mutation and semantic feedback.<n>Our method achieves faster time-to-first-bug, higher semantic diversity, and a competitive number of unique bugs compared to state-of-the-art fuzzers.
  arXiv  Detail & Related papers  (2025-11-06T02:38:24Z)
• Autoregressive Speech Synthesis without Vector Quantization [135.4776759536272]
  We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS)<n>MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition.<n>MELLE mitigates robustness issues by avoiding the inherent flaws of sampling vector-quantized codes.
  arXiv  Detail & Related papers  (2024-07-11T14:36:53Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic Communications [71.63189900803623]
  A novel emergent SC system framework is proposed and is composed of a signaling game for emergent language design and a neuro-symbolic (NeSy) artificial intelligence (AI) approach for causal reasoning. The ESC system is designed to enhance the novel metrics of semantic information, reliability, distortion and similarity.
  arXiv  Detail & Related papers  (2022-10-21T15:33:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.