user avatar
Sebastian Gehrmann
@sebgehr
Making AI trustworthy as Head of Responsible AI in the CTOs office @Bloomberg. Formerly LLMs @ Google Brain / PhD @ Harvard. views my own
New York City
sebastiangehrmann.github.io
Joined November 2013
1,991
Following
6,455
Followers
Posts
  • Pinned
    user avatar
    Sebastian Gehrmann
    @sebgehr
    Feb 3, 2021
    Introducing 💎GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. We are organizing shared tasks for our ACL 2021 workshop - Please consider participating! Website: gem-benchmark.com Paper: arxiv.org/abs/2102.01672 #NLProc 🧵1/X
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Nov 5, 2025
    We are looking for Ph.D. fellows! Bloomberg will fund research and mentor outstanding graduate students across a wide range of Computer Science and AI topics. If you want to be considered, please apply by December 14. Link with information and application details below 👇
    29K
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Nov 30, 2022
    My group is hiring interns for summer 2023. If you are a current PhD student and interested, please email me. Info on internship topics: gideonmann77.github.io/interns-2023.h… There are also multiple open full-time roles in AI Engineering - feel free to reach out :)
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Oct 19, 2022
    We want to identify the capabilities and limitations of LLMs. But which existing tasks are the most challenging? And can we solve them already with newer models and prompting approaches? Our work, led by Mirac Suzgun, investigates these questions: arxiv.org/abs/2210.09261 👇
    A picture of the authors and abstract of the paper "Challenging BIG-Bench tasks and whether chain-of-thought can solve them". The text can be found at https://arxiv.org/abs/2210.09261.
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Feb 10, 2020
    In personal news, today was my first day as a research scientist at @GoogleAI!!! I am so excited to work with all the super smart people on fun #NLProc problems and be part of the New York NLP community. That also means that I officially moved - lmk if you want to get together!
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Nov 3, 2025
    We are looking for excellent PhD students across many topics for our Bloomberg CTO AI Research internship next summer. Link to apply below.
    18K
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Feb 15, 2022
    Listing issues in NLG evaluations turned into a 25 page survey! In “Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text”, @ThiboIbo @eaclark07 and I cover 250+ papers. 📄Link: arxiv.org/abs/2202.06935 Want to learn more?👇
    An illustration of a pipeline in which a model developer sends a network into an evaluation black box and many numbers and figures come out. The developer ignores the results and picks the one that shows state of the art performance.
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Oct 31, 2019
    Best poster of #inlg2019 by Amit Moryossef, Ido Dagan, and @yoavgo on planning for Neural data2text generation
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Oct 23, 2025
    To my friends at meta impacted by the layoffs, we are hiring in London, NYC, and Toronto. Link with jobs and application info below 👇🏼
    35K
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Oct 19, 2019
    In other news, I just defended my Ph.D! Thanks to everyone at Harvard, especially my committee members @srush_nlp, Barbara Grosz, and @pmphlt. If you want to learn more about Human-AI collaboration for NLG, here are my slides (video coming soon): scholar.harvard.edu/files/gehrmann…
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    May 29, 2020
    The ELMo paper? 15 pages. BERT? 16 pages. GPT-2? 24 pages. T5? 53 pages. GPT-3?? 72 pages! arxiv.org/pdf/2005.14165… Showing once and for all that paper sizes keep growing. We really should be concerned about the energy implications, poor trees :(
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    May 27, 2023
    My wife did a thing! So happy for her. We'll move to Philly in a couple months, tips welcome and I'm looking for commuting-to-NYC friends :)
    user avatar
    Samantha McBride
    @Sam_A_McBride
    May 27, 2023
    I am excited to share that I have accepted an assistant professor position in mechanical engineering at the University of Pennsylvania. The McBride lab will investigate interfacial phenomenon and fluid mechanics for water and sustainability! @Penn @PennEngineers
    26K
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Oct 30, 2024
    I'll be hiring an intern working on an evaluation-related topic. If that sounds like you, please fill the form!
    user avatar
    Mark Dredze
    @mdredze
    Oct 29, 2024
    Are you interested in an AI internship at @TechAtBloomberg ? 🏖️🌞😎⛱️ Fill out this form! forms.gle/gv69a26BmA7Mae…
    30K
  • user avatar
    Sebastian Gehrmann
    @sebgehr
    Jul 21, 2019
    5:30am. My fiancee, trying not to wake me up, whispers: "Alexa, turn off the alarm" Alexa, pinnacle of voice assistants, at the volume of a jet engine: "It sounds like you just whispered to me. If you want me to whisper back, please activate the feature in the app!" Just why? 🙃