Elamur Research⌕
☰
home / authors / Markus N. Rabe

Markus N. Rabe

Markus N. Rabe has 3 papers in our library, in 2019–2023, most of them on Reasoning; often with Christian Szegedy, Albert Q. Jiang, Kshitij Bansal.

3 papers in our library · 2019–2023

OpenAlex · ORCID · h-index 18 · 55 works · 1,443 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 567 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #4471

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

🏢GoogleMountain View · United States2018–2022 · 17 papers🎓University of California, BerkeleyBerkeley · United States2015–2019 · 11 papers🎓Saarland UniversitySaarbrücken · Germany2010–2015 · 11 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 3 worksComputational Theory and Mathematics · 2 worksMathematics · 1 workSoftware · 1 work

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work

 Works by year

2020s

20231 paper20221 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Autoformalization with Large Language Models (2022 · 204 citations)
    Turning informal mathematics into machine-checkable form normally requires expert effort, and very little aligned data exists that pairs natural-language math with formal code.
  2. Baldur: Whole-Proof Generation and Repair with Large Language Models (2023 · 175 citations)
    Writing machine-checked proofs for software verification is very costly. Earlier neural provers reduce this by predicting one tactic at a time and searching over proof states, which requires constant back-and-forth between a GPU-hosted model and a CPU-bound proof assistant. Baldur takes a simpler route. It fine-tunes…
  3. HOList: An Environment for Machine Learning of Higher-Order Theorem Proving (2019 · 78 citations)
    Learning-based theorem proving has lacked a shared, large-scale benchmark. Existing proof assistants use incompatible logical foundations, and earlier datasets were either small or scored only with proxy metrics. HOList fills this gap. It is an open-source environment built on the HOL Light interactive prover…

All works

12 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Autoformalization with Large Language ModelsarXiv:2205.12615Yuhuai Wu, Albert Q. Jiang, Wenda Li, et al.2022 · 204 citations
  2. Baldur: Whole-Proof Generation and Repair with Large Language ModelsarXiv:2303.04910Emily First, Markus N. Rabe, Talia Ringer, et al.2023 · 175 citations
  3. Memorizing Transformers ↗arXiv:2203.08913 · no summary yetYuhuai Wu et al.2022 · 163 citations
  4. HOList: An Environment for Machine Learning of Higher-Order Theorem ProvingarXiv:1904.03241Kshitij Bansal, Sarah M. Loos, Markus N. Rabe, et al.2019 · 78 citations
  5. Mathematical Reasoning via Self-supervised Skip-tree Training ↗arXiv:2006.04757 · no summary yetMarkus N. Rabe et al.2020 · 54 citations
  6. LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning ↗arXiv:2101.06223 · no summary yetYuhuai Wu et al.2021 · 39 citations
  7. Learning to Reason in Large Theories without Imitation ↗arXiv:1905.10501 · no summary yetKshitij Bansal et al.2019 · 36 citations
  8. Mathematical Reasoning in Latent Space ↗arXiv:1909.11851 · no summary yetDennis Lee et al.2019 · 33 citations
  9. Graph Representations for Higher-Order Logic and Theorem Proving ↗arXiv:1905.10006 · no summary yetAditya Paliwal et al.2019 · 33 citations
  10. Teaching Temporal Logics to Neural Networks ↗arXiv:2003.04218 · no summary yetChristopher Hahn et al.2020 · 24 citations
  11. Learning Heuristics for Quantified Boolean Formulas through Deep Reinforcement Learning ↗arXiv:1807.08058 · no summary yetGil Lederman et al.2018 · 12 citations
  12. Towards the Automatic Mathematician ↗Lecture notes in computer science · no summary yetMarkus N. Rabe, Christian Szegedy2021 · 8 citations

 Co-authors here

7 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 567 times (of the 149,439 papers whose bibliographies we read); 104 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/markus-n-rabe/