{"ID":2844430,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06468","arxiv_id":"2511.06468","title":"Towards Attention-Aware Large Language Models: Integrating Real-Time Eye-Tracking and EEG for Adaptive AI Responses","abstract":"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.","short_abstract":"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 ide...","url_abs":"https://arxiv.org/abs/2511.06468","url_pdf":"https://arxiv.org/pdf/2511.06468v1","authors":"[\"Dan Zhang\"]","published":"2025-11-09T17:27:31Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}