Towards Attention-Aware Large Language Models: Integrating Real-Time Eye-Tracking and EEG for Adaptive AI Responses
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912696173068288 |
|---|---|
| author | Zhang, Dan |
| author_facet | Zhang, Dan |
| contents | This project proposes an attention-aware LLM that integrates EEG and eye tracking to monitor and measure user attention dynamically. To realize this, the project will integrate real-time EEG and eye-tracking data into an LLM-based interactive system and classify the user's attention state on the fly. The system can identify five attention states: High Attention, Stable Attention, Dropping Attention, Cognitive Overload, and Distraction. It responds accordingly to each state, with a particular focus on adapting to decreased attention, distraction, and cognitive overload to improve user engagement and reduce cognitive load. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06468 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Attention-Aware Large Language Models: Integrating Real-Time Eye-Tracking and EEG for Adaptive AI Responses Zhang, Dan Human-Computer Interaction This project proposes an attention-aware LLM that integrates EEG and eye tracking to monitor and measure user attention dynamically. To realize this, the project will integrate real-time EEG and eye-tracking data into an LLM-based interactive system and classify the user's attention state on the fly. The system can identify five attention states: High Attention, Stable Attention, Dropping Attention, Cognitive Overload, and Distraction. It responds accordingly to each state, with a particular focus on adapting to decreased attention, distraction, and cognitive overload to improve user engagement and reduce cognitive load. |
| title | Towards Attention-Aware Large Language Models: Integrating Real-Time Eye-Tracking and EEG for Adaptive AI Responses |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.06468 |