Facilitating Human Feedback for GenAI Prompt Optimization

Jacob Sherson*, Florent Vinchon

*Corresponding author for this work

Research output: Contribution to book/anthology/report/proceedingBook chapterResearchpeer-review

Abstract

This study investigates the optimization of Generative AI (GenAI) systems through human feedback, focusing on how varying feedback mechanisms influence the quality of GenAI outputs. We devised a Human-AI training loop where 32 students, divided into two groups, evaluated AI-generated responses based on a single prompt. One group assessed a single output, while the other compared two outputs. Preliminary results from this small-scale experiment suggest that comparative feedback might encourage more nuanced evaluations, highlighting the potential for improved human-AI collaboration in prompt optimization. Future research with larger samples is recommended to validate these findings and further explore effective feedback strategies for GenAI systems.

Original languageEnglish
Title of host publicationHHAI 2024 : Hybrid Human AI Systems for the Social Good - Proceedings of the 3rd International Conference on Hybrid Human-Artificial Intelligence
EditorsFabian Lorig, Jason Tucker, Adam Dahlgren Lindstrom, Frank Dignum, Pradeep Murukannaiah, Andreas Theodorou, Pinar Yolum
Number of pages3
PublisherIOS Press BV
Publication dateJun 2024
Pages478-480
ISBN (Electronic)9781643685229
DOIs
Publication statusPublished - Jun 2024
Event3rd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2024 - Hybrid, Malmo, Sweden
Duration: 10 Jun 202414 Jun 2024

Conference

Conference3rd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2024
Country/TerritorySweden
CityHybrid, Malmo
Period10/06/202414/06/2024
SeriesFrontiers in Artificial Intelligence and Applications
Volume386
ISSN0922-6389

Keywords

  • education
  • Generative AI
  • human-machine learning
  • prompt engineering

Fingerprint

Dive into the research topics of 'Facilitating Human Feedback for GenAI Prompt Optimization'. Together they form a unique fingerprint.

Cite this