Elamur Research⌕
☰
home / authors / Thomas Hartvigsen

Thomas Hartvigsen

Thomas Hartvigsen has 5 papers in our library, in 2022–2026, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Maarten Sap, Saadia Gabriel, Zachary Gottesman.

5 papers in our library · 2022–2026

OpenAlex · ORCID · Wikidata · h-index 15 · 88 works · 1,076 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 387 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #3383

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

🎓University of VirginiaCharlottesville · United States2023–2026 · 68 paperscurrent🏢GoogleMountain View · United States2026 · 1 papercurrent🎓Worcester Polytechnic InstituteWorcester · United States2017–2021 · 21 papers🎓Massachusetts Institute of TechnologyCambridge · United States2022–2024 · 17 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2022–2024 · 5 papers🔬Allen Institute for Artificial IntelligenceSeattle · United States2024–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArtificial Intelligence · 5 worksSocial Sciences · 3 worksSociology and Political Science · 2 worksArts and Humanities · 4 worksLanguage and Linguistics · 4 worksSafety Research · 1 workSignal Processing · 1 work

🧭 Topics 5Research subjects and languages the work is about.Bias, fairness & safety · 2 worksSentiment & emotion · 1 workLanguage models & pretraining · 3 worksReasoning · 2 worksEnglish · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Text classification · 1 work

 Works by year

2020s

20261 paper20252 papers20231 paper20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection (2022 · 578 citations)
    Hate speech classifiers often learn a shortcut: they treat any mention of a minority group as a sign of toxicity.
  2. Interpretable Unified Language Checking (2023 · 32 citations)
    Harmful text, whether written by people or produced by LLMs, can be wrong in different ways: it may be false, stereotyping, or hateful.
  3. Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes (2025 · 7 citations)
    The paper asks whether mathematical reasoning in large language models is tied to a separable set of parameters, and whether that set can be located cheaply.
  4. Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English (2025 · 6 citations)
    The paper asks whether large language models reason as well, and explain themselves as well, when a question is written in African American English (AAE) as when it is written in Standard American English (SAE).
  5. Inferring Events from Time Series using Language Models (2026 · 1 citation)
    The paper asks whether large language models can work backwards from a numeric time series to the real-world events that likely produced it.

All works

7 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. ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, et al.2022 · 578 citations
  2. Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetCansu Sen et al.2020 · 79 citations
  3. Interpretable Unified Language CheckingarXiv:2304.03728Tianhua Zhang, Hongyin Luo, Yung-Sung Chuang, et al.2023 · 32 citations
  4. Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesAnnual Meeting of the Association for Computational Linguistics (ACL)Bryan R Christ, Zachary Gottesman, Jonathan Kropko, et al.2025 · 7 citations
  5. Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American EnglisharXiv:2503.04099Runtao Zhou, Guangya Wan, Saadia Gabriel, et al.2025 · 6 citations
  6. Improving Black-box Robustness with In-Context Rewriting ↗arXiv (Cornell University) · no summary yetKyle O'Brien et al.2024 · 3 citations
  7. Inferring Events from Time Series using Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mingtian Tan, Mike A Merrill, Zachary Gottesman, et al.2026 · 1 citation

 Co-authors here

12 of 15 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 387 times (of the 149,439 papers whose bibliographies we read); 94 citing papers with a page here →.

Updated

↑ back to top

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