# ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design

arXiv: https://arxiv.org/abs/2605.10189 · HTML: https://mlsanity.com/paper/2605.10189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Preference optimization for molecular design, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference optimization for molecular design](https://mlsanity.com/alignment/preference-optimization-for-molecular-design/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data](https://mlsanity.com/paper/2404.14367/) (2024)
- [ProGen2: Exploring the Boundaries of Protein Language Models](https://mlsanity.com/paper/2206.13517/) (2022)
- [ProGen: Language Modeling for Protein Generation](https://mlsanity.com/paper/2004.03497/) (2020)
- [A Text-guided Protein Design Framework](https://mlsanity.com/paper/2302.04611/) (2023)
- [ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing](https://mlsanity.com/paper/2402.16445/) (2024)
- [RITA: a Study on Scaling Up Generative Protein Sequence Models](https://mlsanity.com/paper/2205.05789/) (2022)
- [Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training](https://mlsanity.com/paper/2602.12222/) (2026)
- [Annotation-guided Protein Design with Multi-Level Domain Alignment](https://mlsanity.com/paper/2404.16866/) (2024)
- [Steering Protein Language Models](https://mlsanity.com/paper/2509.07983/) (2025)
- [ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning](https://mlsanity.com/paper/2506.07459/) (2025)
- [Controllable Protein Sequence Generation with LLM Preference Optimization](https://mlsanity.com/paper/2501.15007/) (2025)
- [Protein Design with Dynamic Protein Vocabulary](https://mlsanity.com/paper/2505.18966/) (2025)
- [PDFBench: A Benchmark for De novo Protein Design from Function](https://mlsanity.com/paper/2505.20346/) (2025)
- [Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment](https://mlsanity.com/paper/2603.06748/) (2026)

## Abstract (arXiv)

Designing proteins with desired functions or properties represents a core goal in synthetic biology and drug discovery. Recent advances in protein language models (PLMs) have enabled the generation of highly designable protein sequences, while preference alignment provides a promising way to steer designs toward desired functions and properties. Nevertheless, they often trigger catastrophic forgetting of pretrained knowledge, degrading basic designability and failing to balance multiple competing objectives. To address these issues, we draw inspiration from On-Policy Distillation (OPD), an advanced post-training method renowned for mitigating catastrophic forgetting through its mode-seeking nature. In this work, we propose ProteinOPD, a multi-objective preference alignment framework that can effectively balance multiple preference objectives while maintaining the inherent designability of PLMs. ProteinOPD adapts a pretrained PLM into preference-specific teachers and distills their knowledge into a shared student via token-level OPD on the student's own trajectories. During this process, the student is aligned to a unique normalized geometric consensus of weighted teachers while ensuring bounded optimization under conflicts. This bridges the gap for OPD in multi-objective/teacher alignment. Extensive experiments show that ProteinOPD achieves substantial gains on target preference objectives without compromising the designability, with an 8x training speedup over RL-based alignment competitors.