Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2025Proceedings of the Human Factors and Ergonomics Society Annual Meeting

AI-Driven Heuristic Analysis: Enhancing Work Instruction With Generative Models

View Full Paper
Ask AI
Bookmark
Share

Authors

FMFernando MontalvoPSPromise StephensPTPhuoc Thai

Discussion

Loading...

Member takes

Overview

The research reveals AI scoring of workplace instructions shows potential, highlighting areas to improve transparency and reliability.

Key Points

  • AI scoring demonstrated reproducibility despite low agreement with human experts, revealing its potential value.
  • Qualitative analysis indicated the AI's strength in identifying weaknesses in work instructions, outperforming individual evaluators.
  • Human evaluators' high variability led to poor agreement with AI, suggesting room for developing consistent evaluation methods.
  • The research acknowledges the need for ongoing model refinement to enhance AI's detail and transparency in explanations.

Cite This Study

Montalvo et al. (2025) studied this question.

synapsesocial.com/papers/68bb49d26d6d5674bcd001bbhttps://doi.org/10.1177/10711813251369802
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Smarter UX Evaluations? Comparing AI and Human Experts in Usability Analysis2025 · 1 citations
  2. 2Structured Human-AI Teaming for UX Heuristic Evaluation with Human-in-the-Loop Supervision2026
  3. 3Incorporating Human Judgment in AI-Assisted Content Development: The HEAT Heuristic2024 · 10 citations
  4. 4Leveraging AI to Improve Task-specific Biomechanical Safety Instructions2024 · 1 citations
  5. 5Comparative analysis of AI and expert evaluations in engineering design pedagogy2025