Researcher

Bailey Kuehl

Bailey Kuehl is a researcher who works on scientific literature tools, biomedical summarization, and language models. She joined Ai2’s Semantic Scholar team as a Data Science Analyst in 2021 and coauthored MS², a paper on multi-document summarization of medical studies. Her work also includes LongEval, guidelines for evaluating long-form summaries, and the VisualAIze capstone project at UC Berkeley. She coauthored Olmo 3 in 2025 and is a research engineer at Ai2.

Works
49
Citations
497
h-index
12

Publication numbers from OpenAlex, as of 18 October 2026.

Timeline

  1. 2021

    Semantic Scholar analyst

    In 2021, she works as a Data Science Analyst on Ai2’s Semantic Scholar team.

  2. 2021

    Medical study summarization

    MS² is Kuehl’s 2021 paper on multi-document summarization of medical studies.

  3. 2023

    Long-form faithfulness guidelines

    LongEval, coauthored by Kuehl in 2023, sets out guidelines for evaluating faithfulness in long-form summaries.

  4. 2024

    An accessibility capstone

    VisualAIze is Kuehl’s 2024 UC Berkeley MIDS capstone project; the team uses large language models and multimodal datasets to generate airport image descriptions for people with visual impairments.

  5. 2025

    Olmo 3 language models

    Olmo 3 is Kuehl’s 2025 coauthored work, a fully open family of language models at the 7B and 32B parameter scales.

  6. Since 2026

    Research engineer at Ai2

    She is a research engineer at the Allen Institute for Artificial Intelligence, a role she takes up in 2026.

Career

  1. Since 2021Allen Institute for AI (Ai2)Data Science Analyst, Research Engineer
  2. 2023–2025University of California, Berkeley
  3. 2022–2025University of Washington

Education

  1. University of California, BerkeleyMIDS

Most-cited works

  1. MSˆ2: Multi-Document Summarization of Medical Studies2021 · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 83 citations
  2. The Semantic Scholar Open Data Platform2023 · 63 citationsWith Daniel S. Weld and Oren Etzioni
  3. A Search Engine for Discovery of Scientific Challenges and Directions2022 · Proceedings of the AAAI Conference on Artificial Intelligence · 37 citationsWith Daniel S. Weld and Eric Horvitz
  4. MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting2022 · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 37 citations
  5. Generating Scientific Claims for Zero-Shot Scientific Fact Checking2022 · Annual Meeting of the Association for Computational Linguistics (ACL) · 35 citationsWith Isabelle Augenstein

Sources and credits

Photo: We have no published photo of Bailey Kuehl yet. Send us a free-licensed photo.

  1. AI2 Newsletter – December 2021 allenai.org. Checked 18 October 2026.
  2. MSˆ2: Multi-Document Summarization of Medical Studies aclanthology.org. Checked 18 October 2026.
  3. LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization aclanthology.org. Checked 18 October 2026.
  4. VisualAIze: Accessible Spatial Awareness Using AI ischool.berkeley.edu. Checked 18 October 2026.
  5. Olmo 3 arxiv.org. Checked 18 October 2026.
  6. Bailey Kuehl — Lacuna lacuna.tiptreesystems.com. Checked 18 October 2026.