3 papers
cs.CL2026
Understanding Teacher Revisions of Large Language Model-Generated Feedback
Conrad Borchers, Luiz Rodrigues, Newarney Torrezão da Costa +2
Large language models (LLMs) increasingly generate formative feedback for students, yet little is known about how teachers revise this feedback before it reaches learners. Teachers…
cs.CL2025
Enhancing Essay Cohesion Assessment: A Novel Item Response Theory Approach
Bruno Alexandre Rosa, Hilário Oliveira, Luiz Rodrigues +2
Essays are considered a valuable mechanism for evaluating learning outcomes in writing. Textual cohesion is an essential characteristic of a text, as it facilitates the establishme…
cs.HC2025
Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
Guilherme Guerino, Luiz Rodrigues, Bruna Capeleti +3
Heuristic evaluation is a widely used method in Human-Computer Interaction (HCI) to inspect interfaces and identify issues based on heuristics. Recently, Large Language Models (LLM…