LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it often arises in complex, dynamic contexts and cannot be easily captured by post-hoc task outcomes. In this work, we aim to investigate how users’ behavioral patterns correlate with overreliance. We collected interaction logs from 77 participants working with an LLM injected plausible misinformation across three real-world tasks and we assessed overreliance by whether participants detected and corrected these errors. By semantically encoding and clustering segments of user interactions, we identified five behavioral patterns linked to overreliance: users with low overreliance show careful task comprehension and fine-grained navigation; users with high overreliance show frequent copy-paste, skipping initial comprehension, repeated LLM references, coarse locating, and accepting misinformation despite hesitation. We discuss design implications for mitigation.

In this paper, we present a novel, unobtrusive calibration method that leverages the association between eye-movement and text to calibrate eye-tracking devices during natural reading. The calibration process involves an iterative sequence of 3 steps: (1) matching the points of eye-tracking data with the text grids and boundary grids, (2) computing the weight for each point pair, and (3) optimizing the calibration parameters that best align point pairs through gradient descent. During this process, we assume that, from a holistic perspective, the gaze will cover the text area, effectively filling it after sufficient reading. Meanwhile, on a granular level, the gaze duration is influenced by the semantic and positional features of the text. Therefore, factors such as the presence of empty space, the positional features of tokens, and the depth of constituency parsing play important roles in calibration. Our method achieves accuracy error comparable to traditional 7-point mehtod after naturally reading 3 texts, which takes about 51.75 seconds. Moreover, we analyse the impact of different holistic and granular features on the calibration results.

We demonstrate Thermotion, a novel method using thermofluidic composites to design and display thermochromic animation effects on object surfaces. With fluidic channels embedded under the object surfaces, the composites utilize thermofluidic flows to dynamically control the surface temperature as an actuator for thermochromic paints, which enables researchers and designers for the first time to create animations not only on two and three-dimensional surfaces but also on the surface made of a few flexible everyday materials. We demonstrate the fabrication workflow of the composites and the design space of the animation effects. A range of applications is shown leveraging the objects’ dynamic displays both visually and thermally, including dynamic artifacts, teaching aids, and ambient displays. We envision an opportunity to extend thermofluidic composites to other heat-related practices for further dynamic and programmable interactions with temperature.