Sebastian Gehrmann
@sebgehr
Followers
5K
Following
4K
Statuses
2K
Head of Responsible AI, CTO office, @Bloomberg. (he/him) Generating useful natural language, one word at a time. views my own
New York City
Joined November 2013
GEM is so back! Our workshop for Generation, Evaluation, and Metrics is coming to an ACL near you. Evaluation in the world of GenAI is more important than ever, so please consider submitting your amazing work. CfP can be found at
0
6
25
0
0
0
GEM is back!
(22) The Third Workshop on Social Influence in Conversations (SICon 2025) (23)SDP 2025: The 5th Workshop on Scholarly Document Processing (24) Meaningful, Efficient, and Robust Evaluation of LLMs (25) GEM: Natural Language Generation, Evaluation, and Metrics #NLProc #ACL2025NLP
0
5
28
1
0
3
RT @TechAtBloomberg: In today's 7th BlackboxNLP Workshop at #EMNLP2024, research by @icsaAtEd's Jordi Armengol-Estapé, Lingyu Li, @sebgehr,…
0
3
0
Congrats Alex! This was a hard one to write. It took many months to find the right framing and I learned a ton about journalism. But it came out amazing with practical actionable insights all grounded in meticulous analyses. Count this as endorsement of future Prof Spangher :)
Wow feeling soooo lucky to have won 2 outstanding paper awards at EMNLP 2024!!! Both were super fun to work on — both focus planning in creative NLP. Let’s chat! Thank you @mdredze @sebgehr @VioletNPeng @jonathanmay p.s. I AM ON THE FACULTY MARKET THIS YEAR!!
0
2
15
RT @AlexanderSpangh: 🚨New EMNLP paper🚨 with @mdredze @VioletNPeng @sebgehr Training better chain-of-thought in LL…
0
9
0
Missing #EMNLP2024 :( baby at home needs me more, but come find my coauthors! 1) LLM use for Journalists: @AlexanderSpangh 2) Academia, Industry, and LLMs: @gentaiscool 3) Knowledge Localization: @jordiae
1
4
29
I'll be hiring an intern working on an evaluation-related topic. If that sounds like you, please fill the form!
Are you interested in an AI internship at @TechAtBloomberg ? 🏖️🌞😎⛱️ Fill out this form!
8
10
114
I blame BuzzFeed for the proclivity of LLMs to only talk in lists.
1
0
13