# Crowd-SFT: Crowdsourcing for LLM Alignment

arXiv: https://arxiv.org/abs/2506.04063 · HTML: https://mlsanity.com/paper/2506.04063/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [A Marketplace for Data: An Algorithmic Solution](https://mlsanity.com/paper/1805.08125/) (2018)
- [Transparent Contribution Evaluation for Secure Federated Learning on Blockchain](https://mlsanity.com/paper/2101.10572/) (2021)

## Abstract (arXiv)

Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT without extensive annotator training. Our framework promotes incentive fairness via a point-based reward system correlated with Shapley values and guides model convergence through iterative model updates. Our multi-model selection framework demonstrates up to a 55% reduction in target distance over single-model selection, enabling subsequent experiments that validate our point-based reward mechanism's close alignment with Shapley values (a well-established method for attributing individual contributions) thereby supporting fair and scalable participation.