# Preference optimization for molecular design

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

## Key facts

- Preference optimization for molecular design: 19 papers on arXiv since 2023 (data through 14 Oct 2026).
- 2 of its 19 mapped papers (11%) cite “Preference Optimization for Molecular Language Models” (2023, arXiv 2310.12304).
- 1 of its 19 mapped papers (5%) cite “Preference optimization of protein language models as a multi-objective binder design paradigm” (2024, arXiv 2403.04187).
- 1 new papers 17 Sep–14 Oct.

## Most cited here

- [Preference Optimization for Molecular Language Models](https://mlsanity.com/paper/2310.12304/) (2023), cited by 2 papers here
- [Preference optimization of protein language models as a multi-objective binder design paradigm](https://mlsanity.com/paper/2403.04187/) (2024), cited by 1 papers here
- [De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning](https://mlsanity.com/paper/2504.01389/) (2025), cited by 1 papers here
- [PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design](https://mlsanity.com/paper/2509.07150/) (2025), cited by 1 papers here

## New (17 Sep–14 Oct)

- [MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design](https://mlsanity.com/paper/2610.13305/) (2026-10-09)