Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Collins, Katherine M., Kim, Najoung, Bitton, Yonatan, Rieser, Verena, Omidshafiei, Shayegan, Hu, Yushi, Chen, Sherol, Dutta, Senjuti, Chang, Minsuk, Lee, Kimin, Liang, Youwei, Evans, Georgina, Singla, Sahil, Li, Gang, Weller, Adrian, He, Junfeng, Ramachandran, Deepak, Dvijotham, Krishnamurthy Dj
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909352290418688
author Collins, Katherine M.
Kim, Najoung
Bitton, Yonatan
Rieser, Verena
Omidshafiei, Shayegan
Hu, Yushi
Chen, Sherol
Dutta, Senjuti
Chang, Minsuk
Lee, Kimin
Liang, Youwei
Evans, Georgina
Singla, Sahil
Li, Gang
Weller, Adrian
He, Junfeng
Ramachandran, Deepak
Dvijotham, Krishnamurthy Dj
author_facet Collins, Katherine M.
Kim, Najoung
Bitton, Yonatan
Rieser, Verena
Omidshafiei, Shayegan
Hu, Yushi
Chen, Sherol
Dutta, Senjuti
Chang, Minsuk
Lee, Kimin
Liang, Youwei
Evans, Georgina
Singla, Sahil
Li, Gang
Weller, Adrian
He, Junfeng
Ramachandran, Deepak
Dvijotham, Krishnamurthy Dj
contents Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This paper investigates the effectiveness of fine-grained feedback which captures nuanced distinctions in image quality and prompt-alignment, compared to traditional coarse-grained feedback (for example, thumbs up/down or ranking between a set of options). While fine-grained feedback holds promise, particularly for systems catering to diverse societal preferences, we show that demonstrating its superiority to coarse-grained feedback is not automatic. Through experiments on real and synthetic preference data, we surface the complexities of building effective models due to the interplay of model choice, feedback type, and the alignment between human judgment and computational interpretation. We identify key challenges in eliciting and utilizing fine-grained feedback, prompting a reassessment of its assumed benefits and practicality. Our findings -- e.g., that fine-grained feedback can lead to worse models for a fixed budget, in some settings; however, in controlled settings with known attributes, fine grained rewards can indeed be more helpful -- call for careful consideration of feedback attributes and potentially beckon novel modeling approaches to appropriately unlock the potential value of fine-grained feedback in-the-wild.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16807
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation
Collins, Katherine M.
Kim, Najoung
Bitton, Yonatan
Rieser, Verena
Omidshafiei, Shayegan
Hu, Yushi
Chen, Sherol
Dutta, Senjuti
Chang, Minsuk
Lee, Kimin
Liang, Youwei
Evans, Georgina
Singla, Sahil
Li, Gang
Weller, Adrian
He, Junfeng
Ramachandran, Deepak
Dvijotham, Krishnamurthy Dj
Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This paper investigates the effectiveness of fine-grained feedback which captures nuanced distinctions in image quality and prompt-alignment, compared to traditional coarse-grained feedback (for example, thumbs up/down or ranking between a set of options). While fine-grained feedback holds promise, particularly for systems catering to diverse societal preferences, we show that demonstrating its superiority to coarse-grained feedback is not automatic. Through experiments on real and synthetic preference data, we surface the complexities of building effective models due to the interplay of model choice, feedback type, and the alignment between human judgment and computational interpretation. We identify key challenges in eliciting and utilizing fine-grained feedback, prompting a reassessment of its assumed benefits and practicality. Our findings -- e.g., that fine-grained feedback can lead to worse models for a fixed budget, in some settings; however, in controlled settings with known attributes, fine grained rewards can indeed be more helpful -- call for careful consideration of feedback attributes and potentially beckon novel modeling approaches to appropriately unlock the potential value of fine-grained feedback in-the-wild.
title Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation
topic Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.16807