Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs

TL;DR

This paper presents a user-friendly, LLM-driven pipeline for eye-tracking event detection that simplifies analysis, reduces technical barriers, and achieves accuracy comparable to traditional methods.

Contribution

It introduces a code-free, natural language interface for eye-tracking analysis that automates data processing and detector implementation.

Findings

Achieves accuracy comparable to classical detectors on benchmarks.

Reduces technical overhead and coding requirements.

Enables iterative optimization through prompt editing.

Abstract

Gaze event detection is fundamental to vision science, human-computer interaction, and applied analytics. However, current workflows often require specialized programming knowledge and careful handling of heterogeneous raw data formats. Classical detectors such as I-VT and I-DT are effective but highly sensitive to preprocessing and parameterization, limiting their usability outside specialized laboratories. This work introduces a code-free, large language model (LLM)-driven pipeline that converts natural language instructions into an end-to-end analysis. The system (1) inspects raw eye-tracking files to infer structure and metadata, (2) generates executable routines for data cleaning and detector implementation from concise user prompts, (3) applies the generated detector to label fixations and saccades, and (4) returns results and explanatory reports, and allows users to iteratively optimize their code by editing the prompt. Evaluated on public benchmarks, the approach achieves accuracy comparable to traditional methods while substantially reducing technical overhead. The framework lowers barriers to entry for eye-tracking research, providing a flexible and accessible alternative to code-intensive workflows.