arXiv subjects

Kevin Weatherwax

Publications and source records attributed to Kevin Weatherwax.

4 recordsLinked to original sources

arXiv2026

HARP: The Human--AI Research Platform

Large language models (LLMs) have shifted human--computer interaction from `traditional'' interface journeys toward more conversational exchanges. Researchers studying HCI and UI use moderated usability sessions, interviews, surveys, transcript analysis, and static prototypes. However, static prototypes provide limited opportunities to study interaction with live AI systems or systematically control how an LLM behaves across participants and scenarios. Conversation transcripts reveal little about how users formulate, revise, and hesitate over prompts before submission. We designed the Human--AI Research Platform (HARP) for researchers, designers, and anyone who has ever wondered, `What if AI did this?' HARP places participants in controlled mock scenarios with live, configurable AI agents. Researchers can control agent prompts, model parameters, response characteristics, and experimental conditions; trigger surveys at predefined moments; and record prompt composition time, response latency, deletions, and keystroke pauses. Planned capabilities include voice, facial expression, gesture, and, where legally and ethically appropriate, emotion analysis. We illustrate HARP through a study examining how technical specificity and response length affect retention of LLM output. By pairing controllable live agents with behavioral and self-report measures, HARP enables systematic testing of how AI design choices affect users.

cs.HC↗

arXiv2026

Not Too Short, Not Too Long: How LLM Response Length Shapes People's Critical Thinking in Error Detection

Large language models (LLMs) have become common decision-support tools across educational and professional contexts, raising questions about how their outputs shape human critical thinking. Prior work suggests that the amount of AI assistance can influence cognitive engagement, yet little is known about how specific properties of LLM outputs (e.g., response length) impacts users' critical evaluation of information. In this study, we examine whether the length of LLM responses shapes users' accuracy in evaluating LLM-generated reasoning on critical thinking tasks, particularly in interaction with the correctness of the LLM's reasoning. To begin evaluating this, we conducted a within-subjects experiment with 24 participants who completed 15 modified Watson--Glaser critical thinking items, each accompanied by an LLM-generated explanation that varied in length and correctness. Mixed-effects logistic regression revealed a strong and statistically reliable effect of LLM output correctness on participant accuracy, with participants more likely to answer correctly when the LLM's explanation was correct. Response length appeared to moderated this effect: when the LLM output was incorrect, medium-length explanations were associated with higher participant accuracy than either shorter or longer explanations, whereas accuracy remained high across lengths when the LLM output was correct. Together, these findings suggest that response length alone may be insufficient to support critical thinking, and that how reasoning is presented-including a potential advantage of mid-length explanations under some conditions-points to design opportunities for LLM-based decision-support systems that emphasize transparent reasoning and calibrated expressions of certainty.

cs.AI↗

arXiv2026

Material Driven HRI Design: Aesthetics as Explainability

Aesthetics - often treated as secondary to function-guides how people interpret robots' roles. A great deal of robot designs - both real and fictitious - use sleek industrial aesthetics. These feature hard glossy plastics, hiding as much of the underlying mechanical and electrical components as possible, resembling something akin to a nude humanoid figure. This leaves robots as something of a blank slate to which end-users apply coverings to, often based on media of fiction and non-fiction alike. We argue that designers can take cues from fashion to design interaction and set appropriate expectations. Rather than viewing appearance as decoration, we propose that color, texture, and material choices function as interaction signals. These signals can invite or discourage touch, clarify a robot's role, and help align user expectations with a robot's actual capabilities. When done thoughtfully, such cues can create familiarity and legibility; when done poorly, they can lead to wrong expectations. This preliminary paper proposes a framework describing how materials can create explainability by signaling expectations for interaction, task, and environment. We use this framework to do a content analysis of 6 robots.

cs.RO↗

arXiv2021

Remote Observation of Field Work on the Farm

Travel restrictions and social distancing measures make it difficult to observe, monitor or manage physical fieldwork. We describe research in progress that applies technologies for real-time remote observation and conversation in on-road vehicles to observe field work on a farm. We collaborated on a pilot deployment of this project at Kreher Eggs in upstate New York. We instrumented a tractor with equipment to remotely observe and interview farm workers performing vehicle-related work. This work was initially undertaken to allow sustained observation of field work over longer periods of time from geographically distant locales; given our current situation, this work provides a case study in how to perform observational research when geographic and bodily distance have become the norm. We discuss our experiences and provide some preliminary insights for others looking to conduct remote observational research in the field.

cs.CY↗