Elamur Research⌕
☰
home / authors / Rafael Rafailov

Rafael Rafailov

Rafael Rafailov has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining; often with Chelsea Finn, Stefano Ermon, Christopher D. Manning.

2 papers in our library · 2023–2024

OpenAlex · h-index 12 · 53 works · 1,303 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 2,855 times in our library · 7 more in our library without a page yet · ⭐ Paper Stars ranking: #968

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Stanford UniversityStanford · United States2020–2026 · 33 paperscurrent🏢Google DeepMindLondon · United Kingdom2023–2024 · 2 papers🎓Harvard UniversityCambridge · United States2023 · 2 papers🎓University of California, BerkeleyBerkeley · United States2012–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Language model · 1 work

 Works by year

2020s

20241 paperDisentangling Length from Quality in Direct Preference Optimization20231 paperDirect Preference Optimization: Your Language Model is Secretly a Reward Model

 Papers

The most cited first (OpenAlex and our library).

  1. Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2023 · 2,775 citations)
    The paper proposes a way to align a large language model with human preferences without the complex RLHF pipeline.
  2. Disentangling Length from Quality in Direct Preference Optimization (2024 · 99 citations)
    The paper looks at verbosity exploitation in Direct Preference Optimization (DPO). Classical RLHF is known to push models toward longer answers, but this had not been studied for DPO, which trains offline and has no explicit reward model. Existing length-control methods therefore cannot be applied to it directly.

All works

9 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelarXiv:2305.18290Rafael Rafailov, Archit Sharma, Eric Mitchell, et al.2023 · 2,775 citations
  2. Disentangling Length from Quality in Direct Preference OptimizationFindings of the Association for Computational LinguisticsRyan Park, Rafael Rafailov, Stefano Ermon, et al.2024 · 99 citations
  3. From r to Q*: Your Language Model is Secretly a Q-FunctionarXiv:2404.12358 · original ↗ · no summary yetRafael Rafailov et al.2024 · 67 citations
  4. Agent Q: Advanced Reasoning and Learning for Autonomous AI AgentsarXiv:2408.07199 · original ↗ · no summary yetPranav Putta et al.2024 · 57 citations
  5. Generative Reward ModelsarXiv:2410.12832 · original ↗ · no summary yetDakota Mahan et al.2024 · 55 citations
  6. Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-ThoughtarXiv:2501.04682 · original ↗ · no summary yetViolet Xiang et al.2025 · 44 citations
  7. Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language ModelsarXiv:2502.17387 · original ↗ · no summary yetAlon Albalak et al.2025 · 42 citations
  8. An Emulator for Fine-Tuning Large Language Models using Small Language ModelsarXiv:2310.12962 · original ↗ · no summary yetEric Mitchell et al.2023 · 33 citations
  9. Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference LabelsarXiv:2404.14313 · original ↗ · no summary yetJan-Philipp Franken et al.2024 · 15 citations

 Co-authors here

4 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 2,855 times (of the 141,840 papers whose bibliographies we read); 145 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/rafael-rafailov/