Addressing and Visualizing Misalignments in Human Task-Solving Trajectories
This work addresses the problem of enhancing AI models that mimic human reasoning for researchers in AI and human-computer interaction, but it is incremental as it builds on existing trajectory analysis methods.
The study tackled the problem of misalignments in human task-solving trajectories by categorizing them into three types and proposing detection and intention estimation methods, resulting in improved AI model performance in mimicking human reasoning through trajectory alignment.
Understanding misalignments in human task-solving trajectories is crucial for enhancing AI models trained to closely mimic human reasoning. This study categorizes such misalignments into three types: (1) lack of functions to express intent, (2) inefficient action sequences, and (3) incorrect intentions that cannot solve the task. To address these issues, we first formalize and define these three misalignment types in a unified framework. We then propose a heuristic algorithm to detect misalignments in ARCTraj trajectories and analyze their impact hierarchically and quantitatively. We also present an intention estimation method based on our formalism that infers missing alignment between user actions and intentions. Through trajectory alignment, we experimentally demonstrate that AI models trained on human task-solving trajectories improve performance in mimicking human reasoning. Based on hierarchical analysis and experiments, we highlight the importance of trajectory-intention alignment and demonstrate the effectiveness of intention-aligned training.