Facilitating Human Feedback for GenAI Prompt Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929326050508800 |
|---|---|
| author | Sherson, Jacob Vinchon, Florent |
| author_facet | Sherson, Jacob Vinchon, Florent |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Facilitating Human Feedback for GenAI Prompt Optimization Sherson, Jacob Vinchon, Florent Human-Computer Interaction 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. |
| title | Facilitating Human Feedback for GenAI Prompt Optimization |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2404.15304 |