State-of-the-art generalisation testing in NLP. Tag us for a RT of your NLP generalisation paper tweet!
Joined April 2022
- Tweets193
- Following15
- Followers430
- Likes104
GenBench retweeted
so proud of @HayleyRossLing for getting a best paper award at @GenBench this year!! 🎉🪅🎉 I'm sure @TeaAnd_OrCoffee would be too :) check out our paper and share if you think homemade cats are cats!
New paper with @najoungkim and @TeaAnd_OrCoffee testing if LLMs can draw adjective-noun inferences like humans! Turns out they often can, and even generalize to unseen combinations. But they're more optimistic about "artificial intelligence" than humans.
arxiv.org/abs/2410.17482
GenBench retweeted
hi #EMNLP2024🌴!
if you're still around for workshops, come by @GenBench workshop in Brickell (downstairs pavilion)
i'll be chattin about cooking pretraining data🍳 & sharing cat pics🐈⬛ at 11am (local time)
GenBench retweeted
Not EMNLP'd out yet? Join the @GenBench workshop on generalisation in NLP today! 🤩
genbench.org/workshop/
Location: Brickell
GenBench retweeted
If this sounds obvious to you, the @GenBench community is also your community.
If it doesn’t, you should learn about GenBench (and read our meta-analysis nature.com/articles/s42256-0…).
In either case, you’re welcome to join the GenBench Workshop #EMNLP2024 on November 16th ✨
GenBench retweeted
Is your EMNLP-Findings paper a good fit with GenBench and would you like to present it at the workshop? Reach out to us via genbench@googlegroups.com! 📨📨📨 #NLProc #EMNLP2024
GenBench retweeted
The D&I subsidy call for #EMNLP2024 is now available: 2024.emnlp.org/calls/subsidi…
Subsidies available for registration, caregiving, bandwidth, travel and VPN! See website for more details.
Deadline is Friday, October 11th 11:59 (AOE)
GenBench retweeted
Last week, I presented my thesis at @GenBench #EMNLP2023 - the last step of my Masters journey at @EdinburghUni. I feel honoured to have worked with @vernadankers and @iatitov! And I am proud to have received the Howe Prize for the best student in the AI Masters. Miss u Edinburgh
GenBench retweeted
Congrats to our members @Jirui_Qi & @AriannaBisazza for this well-deserved award @GenBench! 🎉
Paper ➡️ arxiv.org/abs/2310.10378 – at Central Region, Singapore
And the best data award to Jirui Qi et al. for their work on crosslingual consistency, titled "Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models". Congrats!
#EMNLP2023 #genbench2023
GenBench retweeted
Very grateful for this @GenBench award given to our work on measuring cross-lingual consistency of factual knowledge in LMs w/ @Jirui_Qi and @raquel_dmg!
And the best data award to Jirui Qi et al. for their work on crosslingual consistency, titled "Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models". Congrats!
#EMNLP2023 #genbench2023
GenBench retweeted
The afternoon programme has started with keynote 3! GenBench has been fun and informative and super well attended thanks to our fantastic line-up of speakers. Join our oral presentations, poster session, panel and best paper award / closing ceremony 🏆 genbench.org/workshop_progra…
GenBench retweeted
I won't be at #EMNLP2023, but Batur (@ospanbatyr) will be presenting our work on exploring training dynamics to obtain better compositional generalization at the @GenBench workshop. Please stop by and say 👋to him if you want to learn more! #NLProc
This Post is from an account that no longer exists. Learn more
GenBench retweeted
Great talk with important takeaways on evaluating LLMs #EMNLP2023 #GenAI #LLMs – at Central Region, Singapore
ALT Problems and solutions for evaluating Ls
Still engaging with all the exciting posters? Join us back for Adina Williams keynote! 🔥 #EMNLP2023 #genbench2023
GenBench retweeted
Busy day today at #EMNLP2023, looking forward to interesting chats! You’ll find me at the LChange workshop in the morning (I’ll give a keynote on word representations at 9:30). In the afternoon between @GenBench (definitely the panel) and #conll2023 (come to our poster at 1:45👇)
📢✨Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue✨ will be at #CoNLL2023 🥳 Proud of this work with @aronmolnr @JumeletJ & @glnmario: my first last-author paper! 🤩✨ #EMNLP2023 arxiv.org/abs/2311.13061
GenBench retweeted
Super excited to be in Singapore to attend #EMNLP2023 with the @GroNlp delegation! See our papers below 👇 We’ll be at @GenBench too
The @GroNLP team is traveling to Singapore to present 8 #EMNLP2023 Main/Findings/Workshops papers! 🐮
Meet @Jirui_Qi @Wietsedv @gsarti_ @AriannaBisazza @khalid_ikh @daniel_sc4 in person and @bylinina @tommaso_caselli at the virtual @emnlpmeeting!
Our papers ⬇️ #EMNLP23 #nlproc
ALT A cow wearing a Dutch hat is traveling to Singapore. The Dutch cow is the logo of the GroNLP group.
GenBench retweeted
I made it to #EMNLP2023, and will be at @GenBench today. My talk ("A sanity check on the emergent properties") starts at 9:15 (Central 3)
Also, I'm looking for a postdoc to work on generalization! Reach out if you'd like to chat during EMNLP (email preferred).
GenBench retweeted
Published today in Nature Machine Intelligence — GenBench is an effort led by AI researchers at Meta that aims to make state-of-the-art generalization testing the new status quo for NLP work.
Read more about the work in @NatMachIntell ➡️ go.nature.com/3rXmzfM
GenBench retweeted
Since our work evaluates generalisation in LLMs, we added a @genbench eval card 9/9
GenBench retweeted
SOTA generalisation testing is what we need!
Show your colleagues the GenBench taxonomy (arxiv.org/abs/2210.03050) and ask them to report evaluation cards (genbench.org/eval_cards) to be upfront about their tests.
Also take them to the first @GenBench workshop at EMNLP2023 :)
