Elamur Research⌕
☰
home / authors / Michael Hahn

Michael Hahn

Michael Hahn has 5 papers in our library, in 2020–2026, most of them on Language models & pretraining, Idioms & multiword expressions; often with Richard Futrell, Christopher D. Manning, Clara Meister.

5 papers in our library · 2020–2026

OpenAlex · ORCID · Wikidata · h-index 14 · 64 works · 718 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 94 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #6600

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

🎓Saarland UniversitySaarbrücken · Germany2021–2026 · 48 papersEmployment since 2022 · Professor (tenure track)current🎓Stanford UniversityStanford · United States2016–2023 · 24 papersEducation 2016–2022 · PhD, Linguistics🎓University of TübingenTübingen · Germany2010–2016 · 9 papersEducation 2010–2013 · B.A., Computational LinguisticsEducation 2011–2014 · B,Sc., MathematicsEducation 2014–2015 · M.Sc., Mathematics🎓University of EdinburghEdinburgh · United Kingdom2016–2019 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 10The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 5 worksComputer Science · 4 worksLanguage and Linguistics · 5 worksArtificial Intelligence · 4 worksComputational Theory and Mathematics · 1 workPsychology · 2 worksDevelopmental and Educational Psychology · 1 workCultural Studies · 1 workExperimental and Cognitive Psychology · 1 workSocial Sciences · 1 work

🧭 Topics 2Research subjects and languages the work is about.Idioms & multiword expressions · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20262 papers20231 paper20211 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. RNNs can generate bounded hierarchical languages with optimal memory (2020 · 65 citations)
    RNN language models capture natural-language syntax well in practice, but the theory behind this has been thin.
  2. Sensitivity as a Complexity Measure for Sequence Classification Tasks (2021 · 26 citations)
    Why can bag-of-words models handle some NLP classification tasks, while others yielded only to large pretrained networks? Hahn, Jurafsky and Futrell answer this by adapting sensitivity, a concept from the analysis of Boolean functions, to natural-language inputs.
  3. A Cross-Linguistic Pressure for Uniform Information Density in Word Order (2023 · 24 citations)
    Languages differ in word order but share statistical tendencies, which are often explained by functional pressures such as dependency length minimization.
  4. Tug-of-war between idioms' figurative and literal interpretations in LLMs (2026 · 1 citation)
    The paper asks how autoregressive transformers handle idioms, which can be read both figuratively (e.g., "to die") and literally (e.g., physically kicking a bucket).
  5. Systematicity between Forms and Meanings across Languages Supports Efficient Communication (2026)
    Research on efficient communication shows that lexicons balance simplicity against accuracy. Its standard formalization, the Information Bottleneck (IB) model, treats word forms as unanalysable symbols. As a result, IB can only detect syncretism (one form shared by several meanings), not partial, systematic overlap…

All works

8 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. Modeling Human Reading with Neural Attention ↗Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · no summary yetMichael Hahn, Frank Keller2016 · 75 citations
  2. RNNs can generate bounded hierarchical languages with optimal memoryConference on Empirical Methods in Natural Language Processing (EMNLP)John Hewitt, Michael Hahn, Surya Ganguli, et al.2020 · 65 citations
  3. An information-theoretic explanation of adjective ordering preferences ↗eScholarship (California Digital Library) · no summary yetMichael Hahn et al.2018 · 43 citations
  4. Sensitivity as a Complexity Measure for Sequence Classification TasksTransactions of the Association for Computational Linguistics (TACL)Michael Hahn, Dan Jurafsky, Richard Futrell2021 · 26 citations
  5. A Cross-Linguistic Pressure for Uniform Information Density in Word OrderTransactions of the Association for Computational Linguistics (TACL)Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, et al.2023 · 24 citations
  6. Tug-of-war between idioms' figurative and literal interpretations in LLMsConference of the European Chapter of the Association for Computational Linguistics (EACL)Soyoung Oh, Xinting Huang, Mathis Pink, et al.2026 · 1 citation
  7. Born a Transformer — Always a Transformer? On the Effect of Pretraining on Architectural Abilities ↗neural information processing systems · no summary yetMayank Jobanputra et al.2025 · 1 citation
  8. Systematicity between Forms and Meanings across Languages Supports Efficient CommunicationAnnual Meeting of the Association for Computational Linguistics (ACL)Doreen Osmelak, Yang Xu, Michael Hahn, et al.2026

 Co-authors here

12 of 14 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 94 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated

↑ back to top

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