Looking forward to the GEM workshop at EMNLP ( Generation Evaluation & Metrics Workshop) where 45 papers on evaluation, generation and metrics were accepted this year! As AC I only saw 6 of them so far, and all the accepted ones presented interesting approaches and valuable contributions - don't miss!

On my way to EMNLP 2025 soon! Join me at Generation Evaluation & Metrics Workshop in Leo 2, 2:30pm on Dec 6 for a presentation about this paper. Thrilled to also contribute as a panelist in WiNLP on "Tackling Misinformation in Generative AI", 11:00am-12:00 in Leo 1 on Dec 6. See you there!

We have three papers led that will be presented at #EMNLP2023 and #GEMWorkshop centered around readability assessment and language model evaluation ✍️📢 Work done by Joseph Imperial and Harish Tayyar Madabushi See you in Singapore! 🌃🇸🇬

1⃣ Stop by my poster presentation at the Generation Evaluation & Metrics Workshop on Dec 6 at 11:00am-12:30pm if you're interested in evaluating summarization for non-news data and how discourse structures can support applications like summarization across text types aclanthology.org/2023.findings-…

Excited🤩for the 3rd GEM Workshop EMNLP 2023! Here's the schedule for Dec 6! (in Singapore🇸🇬time) 9-10:30 Opening Remarks + 6 12min talks 10:30-11🧋Coffee Break 11-12:30🪧Poster Sess 1 12:30-14🍕Break 14-15:30 7 12min talks 15:30-16🧋Covfefe Break :P 16-17:30🪧Poster Sess 2 👇🏻

Excited to present our recent work at the GEM 💎Workshop, EMNLP 2023: “Elo Uncovered: Robustness and Best Practices in Language Model Evaluation” w/ Edward Kim, Beyza Ermiş, Sara Hooker, Marzieh Fadaee 📃: arxiv.org/abs/2311.17295

GEM workshop logistics: we are in LEO 2. Up two escalators and a bit of a walk. We have a rocket chat channel #gem-workshop we will monitor for questions. See you soon!

Finally, Shuhaib Mehri will present his work on instruction tuning for automatic evaluation of generative tasks (arxiv.org/abs/2310.20072) at the GEM workshop on Wed, Dec 6 at 11am SGT. He is applying to grad schools, talk to him if you're recruiting :) 7/7

Today and Now!!! Checkout the fantastic talks and posters lined up at #GEM at #EMNLP2023. If you are interested in generation and evaluating it, come join us in room *Leo* for the exciting schedule today 🤩🤩 #NLProc

Heading to #EMNLP2023 today! Would love to catch up with old friends and meet new folks excited about interpretability, generation, and understanding LM internals 🔧 📜 - My collaborators at Ai2 are presenting our poster on LM eval at the Generation Evaluation & Metrics Workshop at 11am today!

GEM logistics update: The venue has internet issues and we cannot get a stable zoom connection. If you are scheduled to give a talk in the early session and have the ability to go this afternoon instead let us know and we will reshuffle things. We are continuing to try to join.

Check out our poster "Robust Tooling and New Resources for Large Language Model Evaluation via Catwalk" at the Generation Evaluation & Metrics Workshop (11am - 12.30pm, Dec 6). Visit my collaborators from Ai2 there too!

Might be slightly last minute, but I’m thrilled to announce that I will also be giving a talk on our paper in the Generation Evaluation & Metrics Workshop this afternoon! 🤩 The session will start at 2pm, in room Leo 2, but it will also be co-hosted through zoom. Drop by and say hi! 😁

At #EMNLP right now? Check out the GEM💎workshop. A lot of good prompt-based stuff 👇🧵 gem-benchmark.com/workshop

📢Please help us to spread the word: the GEM human evaluation team is launching a new multilingual shared task on data-to-text generation and summarization. More information at gem-benchmark.com/shared_task. We are looking forward to receiving your submissions! #NLProc #NLP