# MallowsPO: Fine-Tune Your LLM with Preference Dispersions

arXiv: https://arxiv.org/abs/2405.14953 · HTML: https://mlsanity.com/paper/2405.14953/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 23 May 2024.

## Placed in

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

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Preference Ranking Optimization for Human Alignment](https://mlsanity.com/paper/2306.17492/) (2023)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2](https://mlsanity.com/paper/2311.10702/) (2023)
- [Nash Learning from Human Feedback](https://mlsanity.com/paper/2312.00886/) (2023)
- [Predictive Entropy Search for Efficient Global Optimization of Black-box Functions](https://mlsanity.com/paper/1406.2541/) (2014)
- [Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data](https://mlsanity.com/paper/2404.14367/) (2024)
- [Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints](https://mlsanity.com/paper/2309.16240/) (2023)
- [Secrets of RLHF in Large Language Models Part II: Reward Modeling](https://mlsanity.com/paper/2401.06080/) (2024)
- [Generalized Preference Optimization: A Unified Approach to Offline Alignment](https://mlsanity.com/paper/2402.05749/) (2024)

## Built on by (most cited first, 18 of 18)

- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey](https://mlsanity.com/paper/2409.11564/) (2024)
- [RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization](https://mlsanity.com/paper/2410.04203/) (2024)
- [Direct Alignment with Heterogeneous Preferences](https://mlsanity.com/paper/2502.16320/) (2025)
- [Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO](https://mlsanity.com/paper/2505.11595/) (2025)
- [Towards a Unified View of Preference Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2409.02795/) (2024)
- [Pairwise Calibrated Rewards for Pluralistic Alignment](https://mlsanity.com/paper/2506.06298/) (2025)
- [ComPO: Preference Alignment via Comparison Oracles](https://mlsanity.com/paper/2505.05465/) (2025)
- [Learning to summarize user information for personalized reinforcement learning from human feedback](https://mlsanity.com/paper/2507.13579/) (2025)
- [An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift](https://mlsanity.com/paper/2601.05882/) (2026)
- [Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling](https://mlsanity.com/paper/2510.23631/) (2025)
- [MixDPO: Modeling Preference Strength for Pluralistic Alignment](https://mlsanity.com/paper/2601.06180/) (2026)
- [Steerable Cultural Preference Optimization of Reward Models](https://mlsanity.com/paper/2606.18606/) (2026)
- [Mallows Model with Learned Distance Metrics: Sampling and Maximum Likelihood Estimation](https://mlsanity.com/paper/2507.08108/) (2025)
- [VisualDeltas: Learning Preferences from Visual Quality Perturbations](https://mlsanity.com/paper/2603.07272/) (2026)
- [A Zeroth-Order Paradigm for LLM Preference Alignment](https://mlsanity.com/paper/2609.19144/) (2026)
- [BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2609.35044/) (2026)

## Abstract (arXiv)

Direct Preference Optimization (DPO) has recently emerged as a popular approach to improve reinforcement learning with human feedback (RLHF), leading to better techniques to fine-tune large language models (LLM). A weakness of DPO, however, lies in its lack of capability to characterize the diversity of human preferences. Inspired by Mallows' theory of preference ranking, we develop in this paper a new approach, the MallowsPO. A distinct feature of this approach is a dispersion index, which reflects the dispersion of human preference to prompts. We show that existing DPO models can be reduced to special cases of this dispersion index, thus unified with MallowsPO. More importantly, we demonstrate (empirically) how to use this dispersion index to enhance the performance of DPO in a broad array of benchmark tasks, from synthetic bandit selection to controllable generations and dialogues, while maintaining great generalization capabilities. MallowsPO is also compatible with other SOTA offline preference optimization methods, boosting nearly 2% extra LC win rate when used as a plugin for fine-tuning Llama3-Instruct.