# Multi-Reference Preference Optimization for Large Language Models

arXiv: https://arxiv.org/abs/2405.16388 · HTML: https://mlsanity.com/paper/2405.16388/

## Key facts

- Cited by 10 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 21 of its 26 references that are in the map.
- First posted on arXiv 26 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, 21 of 21)

- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences](https://mlsanity.com/paper/2403.07230/) (2024)
- [Learning to Constrain Policy Optimization with Virtual Trust Region](https://mlsanity.com/paper/2204.09315/) (2022)

## Built on by (most cited first, 10 of 10)

- [KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity](https://mlsanity.com/paper/2502.01203/) (2025)
- [Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences](https://mlsanity.com/paper/2602.23116/) (2026)
- [Unifying Stable Optimization and Reference Regularization in RLHF](https://mlsanity.com/paper/2602.11523/) (2026)
- [Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences](https://mlsanity.com/paper/2510.15716/) (2025)
- [Intelligently Weighting Multiple Reference Models for Direct Preference Optimization of LLMs](https://mlsanity.com/paper/2512.10040/) (2025)
- [Continual Fine-Tuning of Large Language Models via Program Memory](https://mlsanity.com/paper/2605.13162/) (2026)
- [Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines](https://mlsanity.com/paper/2605.26442/) (2026)
- [The Realignment Problem: When Right becomes Wrong in LLMs](https://mlsanity.com/paper/2511.02623/) (2025)
- [From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models](https://mlsanity.com/paper/2601.06108/) (2026)
- [RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.16431/) (2026)

## Abstract (arXiv)

How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a reference model. Recent approaches, such as direct preference optimization (DPO), have eliminated the need for unstable and sluggish reinforcement learning optimization by introducing close-formed supervised losses. However, a significant limitation of the current approach is its design for a single reference model only, neglecting to leverage the collective power of numerous pretrained LLMs. To overcome this limitation, we introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models, substantially enhancing preference learning capabilities compared to the single-reference DPO. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance. Furthermore, MRPO effectively finetunes LLMs to exhibit superior performance in several downstream natural language processing tasks such as GSM8K and TruthfulQA.