mlsanityData to 7 Oct 2026

Preference optimization for molecular design

19 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: protein, molecular, optimization, protein language, design

Key facts. Preference optimization for molecular design: 19 papers on arXiv since 2023 (data through 7 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).

What’s new

Nothing new since 17 Sep. Latest: 29 Jun 2026.

Foundations

Most cited by papers here

  1. Preference Optimization for Molecular Language Models2023cited by 2 here
  2. Preference optimization of protein language models as a multi-objective binder design paradigm2024cited by 1 here
  3. De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning2025cited by 1 here
  4. PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design2025cited by 1 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2017Deep reinforcement learning from human preferencescited by 4 here
  2. 2019Fine-Tuning Language Models from Human Preferencescited by 3 here
  3. 2020Learning to summarize from human feedbackcited by 2 here
  4. 2022Training language models to follow instructions with human feedbackcited by 9 here
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 7 here
  6. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 3 here
  7. 2023Preference Ranking Optimization for Human Alignmentcited by 2 here
  8. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 2 here
  9. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 2 here
15 more it builds on, not in this chain
  1. 2022Improving alignment of dialogue agents via targeted human judgementscited by 1 here
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 1 here
  3. 2023Direct Preference-based Policy Optimization without Reward Modelingcited by 1 here
  4. 2023Pretraining Language Models with Human Preferencescited by 1 here
  5. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 1 here
  6. 2023LIMA: Less Is More for Alignmentcited by 1 here
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 17 here
  8. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 1 here
  9. 2023Statistical Rejection Sampling Improves Preference Optimizationcited by 1 here
  10. 2023Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraintscited by 1 here
  11. 2023Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimizationcited by 1 here
  12. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 3 here
  13. 2023Preference Optimization for Molecular Language Modelscited by 2 here
  14. 2023Nash Learning from Human Feedbackcited by 1 here
  15. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 1 here

The 24 most cited of 44.

Browse

15 of 19, ranked 6–20

  1. 5Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations20260
  2. 6Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models20260
  3. 7ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design20260
  4. 8Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation20260
  5. 9Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization20260
  6. 10Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision20260
  7. 11AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization20250
  8. 12Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization20250
  9. 13Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization20250
  10. 14g-DPO: Scalable Preference Optimization for Protein Language Models20250
All 15
  1. 15Preference Learning from Physics-Based Feedback: Tuning Language Models to Design BCC/B2 Superalloys20250
  2. 16ALMol: Aligned Language-Molecule Translation LLMs through Offline Preference Contrastive Optimisation20240
  3. 17Aligning Transformers with Continuous Feedback via Energy Rank Alignment20240
  4. 18SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration20240
  5. 19Harnessing Preference Optimisation in Protein LMs for Hit Maturation in Cell Therapy20240