# Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

arXiv: https://arxiv.org/abs/2402.09872 · HTML: https://mlsanity.com/paper/2402.09872/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis](https://mlsanity.com/paper/1904.01310/) (2019)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [Text to Image Generation with Semantic-Spatial Aware GAN](https://mlsanity.com/paper/2104.00567/) (2021)
- [Intrinsic Image Popularity Assessment](https://mlsanity.com/paper/1907.01985/) (2019)

## Built on by (most cited first, 8 of 8)

- [ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization](https://mlsanity.com/paper/2406.04312/) (2024)
- [Alignment of Diffusion Models: Fundamentals, Challenges, and Future](https://mlsanity.com/paper/2409.07253/) (2024)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [ByteEdit: Boost, Comply and Accelerate Generative Image Editing](https://mlsanity.com/paper/2404.04860/) (2024)
- [CAP: Evaluation of Persuasive and Creative Image Generation](https://mlsanity.com/paper/2412.10426/) (2024)
- [Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation](https://mlsanity.com/paper/2602.22570/) (2026)
- [IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance](https://mlsanity.com/paper/2509.26231/) (2025)
- [GuessBench: Sensemaking Multimodal Creativity in the Wild](https://mlsanity.com/paper/2506.00814/) (2025)

## Abstract (arXiv)

Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to engage and contribute with content. The recent progress of text-conditioned image synthesis has ushered in a collaborative era where AI empowers users to craft original visual artworks seeking community validation. Nevertheless, assessing these models in the context of collective community preference introduces distinct challenges. Existing evaluation methods predominantly center on limited size user studies guided by image quality and prompt alignment. This work pioneers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework that leverages implicit feedback from social network users engaged in creative editing of generated images. We embark on an extensive journey of dataset curation and refinement, drawing from Picsart: an online visual creation and editing platform, yielding a first million-user-scale dataset of implicit human preferences for user-generated visual art named Picsart Image-Social. Our analysis exposes the shortcomings of current metrics in modeling community creative preference of text-to-image models' outputs, compelling us to introduce a novel predictive model explicitly tailored to address these limitations. Rigorous quantitative experiments and user study show that our Social Reward model aligns better with social popularity than existing metrics. Furthermore, we utilize Social Reward to fine-tune text-to-image models, yielding images that are more favored by not only Social Reward, but also other established metrics. These findings highlight the relevance and effectiveness of Social Reward in assessing community appreciation for AI-generated artworks, establishing a closer alignment with users' creative goals: creating popular visual art. Codes can be accessed at https://github.com/Picsart-AI-Research/Social-Reward