Hi folks at #ACL2023 Do you know someone interested in PhD programs in #nlproc? We'd love to have them apply to Johns Hopkins! Our growing JHU CLSP faculty (almost 30!) now include Daniel Khashabi 🕊️ and Anjalie Field clsp.jhu.edu/apply-for-phd/…

I'm at #ACL2023 all week; feel free to talk to me or any of my JHU colleagues here about PhD opportunities. If you're mystified about the process, first see cs.jhu.edu/~jason/advice/…

We tried a whole bunch of sensible ways to improve large language model decoding, and this was the one that actually worked. Virtual poster today, Wed, 11am ET at #ACL2023. virtual2023.aclweb.org/paper_P511.html

🧵 A recap of JHU CS at #ACL2023! (1/10) Congrats to Daniel Khashabi 🕊️ & team for their Outstanding Paper Award for "The Tail the Wagging the Dog," an investigation into benchmarking social bias in datasets. Read more here: arxiv.org/pdf/2210.10040…

Read this whole thread, and apply to join us!

Dear ACL community, ACL is considering multiple proposals to change its anonymity period policy. It seeks immediate feedback from the community about the proposed changes. Please add your voice until Friday, September 22nd (AOE): aclweb.org/portal/content… #NLProc

If you can break your AI problem down, an LLM is the 3D printer that can quickly create modules for your subtasks. No module should bear too much load, as they're all made of cheap plastic. But a 3D printer has countless uses. (Our previous 3D printer was MTurk.)

Thrilled to (finally) be able to share our paper: 🐑 Do language models know when they're hallucinating? TL;DR answer: yes! 🔗: arxiv.org/abs/2312.17249, and a🧵 w/ Semantic Machines Microsoft Research: Benjamin Van Durme & Jason Eisner & Chris Kedzie

Great last-minute summer opportunity on LLMs for social good / democracy! (If you're an #NLProc PhD student.) Please retweet. (Team includes Jason Eisner Daniel Khashabi 🕊️ Ziang Xiao Andrew Perrin + students. 8 weeks alongside 3 other teams: fun, meaningful, educational, social.)

New #ACL2024 paper: LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error (Boshi Wang's internship work at Microsoft Semantic Machines) I like this work because it takes home an important insight: synthetic data + post-training is critical for agents.