Saved in:
Bibliographic Details
Main Authors: Murhekar, Akshaj, Liu, Christina, Mishra, Abhijit, Roychowdhury, Shounak, Gwizdka, Jacek
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.17109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911524668309504
author Murhekar, Akshaj
Liu, Christina
Mishra, Abhijit
Roychowdhury, Shounak
Gwizdka, Jacek
author_facet Murhekar, Akshaj
Liu, Christina
Mishra, Abhijit
Roychowdhury, Shounak
Gwizdka, Jacek
contents Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. 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, resulting in expensive training pipelines, limited accessibility, and potential exposure of sensitive neural data. We introduce SENSE (SEmantic Neural Sparse Extraction), a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning. SENSE decouples decoding into two stages: on-device semantic retrieval and prompt-based language generation. EEG signals are locally mapped to a discrete textual space to extract a non-sensitive Bag-of-Words (BoW), which conditions an off-the-shelf LLM to synthesize fluent text in a zero-shot manner. The EEG-to-keyword module contains only ~6M parameters and runs fully on-device, ensuring raw neural signals remain local while only abstract semantic cues interact with language models. Evaluated on a 128-channel EEG dataset across six subjects, SENSE matches or surpasses the generative quality of fully fine-tuned baselines such as Thought2Text while substantially reducing computational overhead. By localizing neural decoding and sharing only derived textual cues, SENSE provides a scalable and privacy-aware retrieval-augmented architecture for next-generation BCIs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17109
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
Murhekar, Akshaj
Liu, Christina
Mishra, Abhijit
Roychowdhury, Shounak
Gwizdka, Jacek
Machine Learning
Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. 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, resulting in expensive training pipelines, limited accessibility, and potential exposure of sensitive neural data. We introduce SENSE (SEmantic Neural Sparse Extraction), a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning. SENSE decouples decoding into two stages: on-device semantic retrieval and prompt-based language generation. EEG signals are locally mapped to a discrete textual space to extract a non-sensitive Bag-of-Words (BoW), which conditions an off-the-shelf LLM to synthesize fluent text in a zero-shot manner. The EEG-to-keyword module contains only ~6M parameters and runs fully on-device, ensuring raw neural signals remain local while only abstract semantic cues interact with language models. Evaluated on a 128-channel EEG dataset across six subjects, SENSE matches or surpasses the generative quality of fully fine-tuned baselines such as Thought2Text while substantially reducing computational overhead. By localizing neural decoding and sharing only derived textual cues, SENSE provides a scalable and privacy-aware retrieval-augmented architecture for next-generation BCIs.
title SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
topic Machine Learning
url https://arxiv.org/abs/2603.17109