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.
View on arXiv@article{mishra2025_2410.07507,
title={ Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) },
author={ Abhijit Mishra and Shreya Shukla and Jose Torres and Jacek Gwizdka and Shounak Roychowdhury },
journal={arXiv preprint arXiv:2410.07507},
year={ 2025 }
}