Thomas Kosch

but none the wiser: The disconnect between performance and metacognition

Does Great Power Come with Great Explainability? Comparing Explanation Strategies for Automated Program Diagnosis

Debugging is an important activity in software development, yet providing actionable and comprehensible explanations for program failures remains challenging. Automated tools such as ALHAZEN and AVICENNA address this by using distinct strategies: ALHAZEN employs binary decision trees to show failure-inducing conditions...

EEG and Eye-Tracking Evidence That AI Disclosure Shapes Face Evaluation

A validated stimulus set and evidence that attributed origin shapes face processing is provided, with implications for disclosure design and Affective processing and initial gaze orienting were unchanged, but labels altered visual exploration.

A Modular Workflow for Multimodal Reading Experiments

We introduce a web-based modular workflow for real-time multimodal experiments in naturalistic online reading. The workflow integrates eye tracking, EEG, and interaction data from mouse and keyboard, synchronizes them via Lab Streaming Layer, and links gaze to browser-based text at the word, sentence, and AOI levels. I...

How Did Writing Change At CHI? Analyzing 44 Years of CHI Writing Before and After the Introduction of Large Language Models

The availability of Large Language Models (LLMs) reshaped scientific discourse at a linguistic level. LLMs are assumed to homogenize academic writing, flattening it into a single generic lexical register. To understand how CHI writing has changed since the public release of LLMs, we analyzed full texts of 14,262 archiv...

Nobody Talks About the Prompt Club: Evaluating Diverse Persona Generation Through System Prompts and Guidelines

Personas are widely used to represent users' motivations, goals, and needs, yet the perspectives of underrepresented groups are rarely addressed in human-centered design. Large Language Models (LLMs) promise to generate personas from vast datasets, but achieving genuine diversity and accurate representation requires de...

Available but Unclaimed: An Empirical Study of Human-AI Synergy

Evaluating LLMs in interaction with humans and designing support for selective deference that preserves independent reasoning motivate evaluating LLMs in interaction with humans.

Does Great Power Come with Great Explainability? Comparing Explanation Strategies for Automated Program Diagnosis

AlHAZEN and AVICENNA show that effective debugging tools have tradeoffs between accuracy and interpretability to support developers’ decision-making in increasingly complex software environments.