EEG-Based Brain-LLM Interface for Human Preference Aligned Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912971300536320 |
|---|---|
| author | Zhang, Junzi Shen, Jianing Tu, Weijie Zhang, Yi Zhang, Hailin Gedeon, Tom Jiang, Bin Yao, Yue |
| author_facet | Zhang, Junzi Shen, Jianing Tu, Weijie Zhang, Yi Zhang, Hailin Gedeon, Tom Jiang, Bin Yao, Yue |
| contents | Large language models (LLMs) are becoming an increasingly important component of human--computer interaction, enabling users to coordinate a wide range of intelligent agents through natural language. While language-based interfaces are powerful and flexible, they implicitly assume that users can reliably produce explicit linguistic input, an assumption that may not hold for users with speech or motor impairments, e.g., Amyotrophic Lateral Sclerosis (ALS). In this work, we investigate whether neural signals can be used as an alternative input to LLMs, particularly to support those socially marginalized or underserved users. We build a simple brain-LLM interface, which uses EEG signals to guide image generation models at test time. Specifically, we first train a classifier to estimate user satisfaction from EEG signals. Its predictions are then incorporated into a test-time scaling (TTS) framework that dynamically adapts model inference using neural feedback collected during user evaluation. The experiments show that EEG can predict user satisfaction, suggesting that neural activity carries information on real-time preference inference. These findings provide a first step toward integrating neural feedback into adaptive language-model inference, and hopefully open up new possibilities for future research on adaptive LLM interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16897 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EEG-Based Brain-LLM Interface for Human Preference Aligned Generation Zhang, Junzi Shen, Jianing Tu, Weijie Zhang, Yi Zhang, Hailin Gedeon, Tom Jiang, Bin Yao, Yue Signal Processing Computation and Language Human-Computer Interaction Machine Learning Neurons and Cognition Large language models (LLMs) are becoming an increasingly important component of human--computer interaction, enabling users to coordinate a wide range of intelligent agents through natural language. While language-based interfaces are powerful and flexible, they implicitly assume that users can reliably produce explicit linguistic input, an assumption that may not hold for users with speech or motor impairments, e.g., Amyotrophic Lateral Sclerosis (ALS). In this work, we investigate whether neural signals can be used as an alternative input to LLMs, particularly to support those socially marginalized or underserved users. We build a simple brain-LLM interface, which uses EEG signals to guide image generation models at test time. Specifically, we first train a classifier to estimate user satisfaction from EEG signals. Its predictions are then incorporated into a test-time scaling (TTS) framework that dynamically adapts model inference using neural feedback collected during user evaluation. The experiments show that EEG can predict user satisfaction, suggesting that neural activity carries information on real-time preference inference. These findings provide a first step toward integrating neural feedback into adaptive language-model inference, and hopefully open up new possibilities for future research on adaptive LLM interaction. |
| title | EEG-Based Brain-LLM Interface for Human Preference Aligned Generation |
| topic | Signal Processing Computation and Language Human-Computer Interaction Machine Learning Neurons and Cognition |
| url | https://arxiv.org/abs/2603.16897 |