# Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback

arXiv: https://arxiv.org/abs/2503.08942 · HTML: https://mlsanity.com/paper/2503.08942/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 45 of its 67 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 45)

- [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)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons](https://mlsanity.com/paper/2301.11270/) (2023)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Nash Learning from Human Feedback](https://mlsanity.com/paper/2312.00886/) (2023)
- [Optimization, Learning, and Games with Predictable Sequences](https://mlsanity.com/paper/1311.1869/) (2013)
- [Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data](https://mlsanity.com/paper/2404.14367/) (2024)
- [Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences](https://mlsanity.com/paper/2404.03715/) (2024)
- [Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints](https://mlsanity.com/paper/2309.16240/) (2023)
- [Generalized Preference Optimization: A Unified Approach to Offline Alignment](https://mlsanity.com/paper/2402.05749/) (2024)
- [A Minimaximalist Approach to Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2401.04056/) (2024)
- [Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer](https://mlsanity.com/paper/2405.16436/) (2024)
- [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://mlsanity.com/paper/2405.21046/) (2024)
- [Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization](https://mlsanity.com/paper/1807.04252/) (2018)
- [Is RLHF More Difficult than Standard RL?](https://mlsanity.com/paper/2306.14111/) (2023)
- [Human Alignment of Large Language Models through Online Preference Optimisation](https://mlsanity.com/paper/2403.08635/) (2024)
- [Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization](https://mlsanity.com/paper/2407.13399/) (2024)

## Built on by (most cited first, 16 of 16)

- [Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO](https://mlsanity.com/paper/2505.19770/) (2025)
- [Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game](https://mlsanity.com/paper/2512.16626/) (2025)
- [Multiplayer Nash Preference Optimization](https://mlsanity.com/paper/2509.23102/) (2025)
- [ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction](https://mlsanity.com/paper/2505.17691/) (2025)
- [Proximal Point Nash Learning from Human Feedback](https://mlsanity.com/paper/2505.19731/) (2025)
- [Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function](https://mlsanity.com/paper/2506.03066/) (2025)
- [Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback](https://mlsanity.com/paper/2512.24818/) (2025)
- [From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models](https://mlsanity.com/paper/2601.06108/) (2026)
- [Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling](https://mlsanity.com/paper/2601.08777/) (2026)
- [Towards General Preference Alignment: Diffusion Models at Nash Equilibrium](https://mlsanity.com/paper/2605.04494/) (2026)
- [Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment](https://mlsanity.com/paper/2605.17342/) (2026)
- [Bilevel Optimization over Saddle Points of Zero-Sum Markov Games](https://mlsanity.com/paper/2605.26654/) (2026)
- [Efficient Exploration for Iterative Nash Preference Optimization](https://mlsanity.com/paper/2606.01382/) (2026)
- [Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning](https://mlsanity.com/paper/2607.06151/) (2026)
- [Inference-Time Nash Alignment](https://mlsanity.com/paper/2609.08082/) (2026)
- [Robust Nash Alignment under Preference Uncertainty](https://mlsanity.com/paper/2610.00715/) (2026)

## Abstract (arXiv)

Reinforcement learning from human feedback (RLHF) has become essential for improving language model capabilities, but traditional approaches rely on the assumption that human preferences follow a transitive Bradley-Terry model. This assumption fails to capture the non-transitive nature of populational human preferences. Nash learning from human feedback (NLHF), targeting non-transitive preferences, is a problem of computing the Nash equilibrium (NE) of the two-player constant-sum game defined by the human preference. We introduce Extragradient preference optimization (EGPO), a novel algorithm for NLHF achieving last-iterate linear convergence to the NE of KL-regularized games and polynomial convergence to the NE of original games, while being robust to noise. Unlike previous approaches that rely on nested optimization, we derive an equivalent implementation using gradients of an online variant of the identity preference optimization (IPO) loss, enabling more faithful implementation for neural networks. Our empirical evaluations demonstrate EGPO's superior performance over baseline methods when training for the same number of epochs, as measured by pairwise win-rates using the ground truth preference. These results validate both the theoretical strengths and practical advantages of EGPO for language model alignment with non-transitive human preferences.