Elamur Research⌕
☰
home / authors / Matthias Assenmacher

Matthias Assenmacher

Matthias Assenmacher has 6 papers in our library, in 2024–2026, most of them on Language models & pretraining, Reasoning, Text generation; often with Barbara Plank, Andreas Stephan, Anna-Carolina Haensch.

6 papers in our library · 2024–2026

OpenAlex · ORCID · h-index 8 · 103 works · 222 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 31 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #8369

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

🎓Ludwig-Maximilians-Universität MünchenMunich · Germany2016–2026 · 72 papersEmploymentcurrent🎓Munich Center for Machine LearningMunich · Germany2023–2026 · 33 paperscurrent

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).Artificial Intelligence · 6 worksComputer Science · 6 worksArts and Humanities · 5 worksLanguage and Linguistics · 5 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 4Research subjects and languages the work is about.Text generation · 1 workLanguage models & pretraining · 2 worksReasoning · 2 worksInformation retrieval & search · 1 work

 Works by year

2020s

20263 papers20252 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation (2025 · 12 citations)
    LLMs output token probabilities, and the decoding step that turns them into text is often left at default settings even though it strongly shapes output quality.
  2. Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study (2025 · 10 citations)
    The paper tests whether LLMs show "algorithmic fidelity", meaning whether they can mimic how specific German population groups answer an open-ended survey question.
  3. More Labels or Cases? Assessing Label Variation in Natural Language Inference (2024 · 8 citations)
    The paper argues that summarizing many crowd votes in NLI, either as a majority label or as raw class frequencies, gives an unreliable picture of how uncertain an instance's label really is.
  4. promptolution: A Unified, Modular Framework for Prompt Optimization (2026 · 2 citations)
    Automatic prompt optimization can substantially boost LLM task performance, but it is hard to adopt. Most optimizers live in isolated, poorly maintained research repositories. Existing libraries are closed-source, implement only one algorithm, or force applications into their own abstractions (as DSPy does). The…
  5. Enhancing Retrieval via Cognitively Motivated Document Expansion (2026)
    The paper asks whether LLMs can strengthen first-stage document retrieval by rewriting the corpus rather than the query, an approach the authors note has received less attention than query expansion.
  6. Reinforcement Learning for Latent-Space Thinking in LLMs (2026)
    The paper asks whether reinforcement learning can improve LLMs that "think" in continuous hidden states instead of writing out discrete chain-of-thought tokens.

All works

9 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

  1. Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text GenerationInternational Conference on Computational Linguistics (COLING)Esteban Garces Arias, Meimingwei Li, Christian Heumann, et al.2025 · 12 citations
  2. Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case StudyAnnual Meeting of the Association for Computational Linguistics (ACL)Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch, et al.2025 · 10 citations
  3. More Labels or Cases? Assessing Label Variation in Natural Language InferenceWorkshop on Understanding Implicit and Underspecified LanguageCornelia Gruber, Katharina Hechinger, Matthias Assenmacher, et al.2024 · 8 citations
  4. taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades ↗Findings of the Association for Computational Linguistics: ACL 2025 · no summary yetStefanie Urchs et al.2025 · 3 citations
  5. promptolution: A Unified, Modular Framework for Prompt OptimizationConference of the European Chapter of the Association for Computational Linguistics (EACL)Tom Zehle, Timo Heiß, Moritz Schlager, et al.2026 · 2 citations
  6. Enhancing Retrieval via Cognitively Motivated Document ExpansionEdition of the Swiss Text Analytics ConferenceGiacomo Loss, Andreas Stephan, Matthias Assenmacher2026
  7. Reinforcement Learning for Latent-Space Thinking in LLMsEdition of the Swiss Text Analytics ConferenceEnes Özeren, Matthias Assenmacher2026
  8. Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan ↗Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities · no summary yetAhan Chatterjee et al.2026
  9. Can Calibration of Positional Encodings Enhance Long Context Utilization? ↗Findings of the Association for Computational Linguistics: EACL 2026 · no summary yetTom Zehle, Matthias Aßenmacher2026

 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 31 times (of the 149,439 papers whose bibliographies we read); 11 citing papers with a page here →.

Updated

↑ back to top

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