@inproceedings{mishra-etal-2025-thought2text,
    title = "{T}hought2{T}ext: Text Generation from {EEG} Signal using Large Language Models ({LLM}s)",
    author = "Mishra, Abhijit  and
      Shukla, Shreya  and
      Torres, Jose  and
      Gwizdka, Jacek  and
      Roychowdhury, Shounak",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.207/",
    pages = "3747--3759",
    ISBN = "979-8-89176-195-7",
    abstract = "Decoding and expressing brain activity in a comprehensible form is a challenging frontier in AI. This paper presents *Thought2Text*, which uses instruction-tuned Large Language Models (LLMs) fine-tuned with EEG data to achieve this goal. The approach involves three stages: (1) training an EEG encoder for visual feature extraction, (2) fine-tuning LLMs on image and text data, enabling multimodal description generation, and (3) further fine-tuning on EEG embeddings to generate text directly from EEG during inference. Experiments on a public EEG dataset collected for six subjects with image stimuli and text captions demonstrate the efficacy of multimodal LLMs (*LLaMA-v3*, *Mistral-v0.3*, *Qwen2.5*), validated using traditional language generation evaluation metrics, as well as *fluency* and *adequacy* measures. This approach marks a significant advancement towards portable, low-cost ``thoughts-to-text'' technology with potential applications in both neuroscience and natural language processing."
}