From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants
This addresses the need for more adaptive AI assistants in educational or cognitive support settings, though it is incremental as it builds on existing multimodal and gaze-tracking technologies.
The researchers tackled the problem of LLM assistants lacking behavioral context by developing a gaze-aware AI assistant that uses egocentric video with gaze overlays to identify user difficulties and provide targeted assistance. In a study with 36 participants, it significantly improved recall accuracy, personalized assessments, and interaction efficiency compared to a text-only assistant.
Current LLM assistants are powerful at answering questions, but they have limited access to the behavioral context that reveals when and where a user is struggling. We present a gaze-grounded multimodal LLM assistant that uses egocentric video with gaze overlays to identify likely points of difficulty and target follow-up retrospective assistance. We instantiate this vision in a controlled study (n=36) comparing the gaze-aware AI assistant to a text-only LLM assistant. Compared to a conventional LLM assistant, the gaze-aware assistant was rated as significantly more accurate and personalized in its assessments of users' reading behavior and significantly improved people's ability to recall information. Users spoke significantly fewer words with the gaze-aware assistant, indicating more efficient interactions. Qualitative results underscored both perceived benefits in comprehension and challenges when interpretations of gaze behaviors were inaccurate. Our findings suggest that gaze-aware LLM assistants can reason about cognitive needs to improve cognitive outcomes of users.