home.social

#acl2024 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #acl2024, aggregated by home.social.

  1. How to make powerful LLMs understand graphs and their structure?🕸️ With Graph Language Models!
    They take a pre-trained LLM and fit it with the ability to process graphs. Watch if you're curious!👇
    📺 youtu.be/JcHeaONGbmQ

    (Hint: it's about position embeddings, as the author explained at #ACL2024 🔴)

  2. Are LLMs any good at self-referential statements such as “This sentence has 5 words”?
    We recorded the #ACL2024 poster presentation of the paper „I am a Strange Dataset: Metalinguistic Tests for Language Models” by Tristan Thrush, Jared Moore, Miguel Monares, Christopher Potts, Douwe Kiela.

    Here’s what it’s all about! 👇
    📺 youtu.be/m_nEIsQBh_c

  3. At the ACL, we recorded the poster presentation of the paper challenging Noam Chomsky's claim about LLMs! 🫢
    📺 youtu.be/8lU6dGqR26s

    This paper, entitled “Mission: Impossible language models”, won an #ACL2024 best paper award.

    Congrats to @JulieKallini @isabelpapad @rljfutrell @kmahowald @ChrisGPotts ! 👏

  4. On the #acl2024 Whova app, I made a "Support group for people who can't stop making currency puns" group, check it out, there's even a poll.

  5. I’m in Bangkok for #ACL2024 and will talk about Legal NLP:

    On Monday I present our corpus and paper AGB-DE (arxiv.org/abs/2406.06809) at the third poster session.

    On Thursday I will talk about teaching NLP in Law School as part of the Workshop on Teaching NLP.

    If you’re at ACL and interested in Legal NLP (or NLP 4 Social Good, Teaching NLP, Disagreement and Perspectivism, other cool applications or just want to have a chat) stop by!

  6. How might we envision NLP for *intercultural* climate communication? Please see our paper at the forthcoming ClimateNLP workshop: openreview.net/pdf?id=LIraXyxh #nlproc #acl2024 #ClimateNLP

  7. RT @irenelizihui: 📢 Glad to share that we will present 3 papers in #ACL2024 🎉
    ⭐️1. Evaluating Large Language Models on Wikipedia-Style Sur…

    via twitter.com/WikiResearch/statu

  8. The 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM), to be held on August 15, 2024, co-located with ACL 2024, Bangkok, Thailand.

    Call for Participation
    Submission Deadline: May 20, 2024 at 23:59, UTC -12h, AoE

    website: kallmworkshop.github.io/kallm2

    #knowledgegraphs #semanticweb #llms #generativeAI #ACL2024 #nlp #conference

  9. 🎉 We developed a prompting method for improved (and more human-like) LLM reasoning and applied it to hybrid question answering, surpassing the GPT-4 baseline. 🚀

    Thanks to my co-authors Dhananjay, Preetam and @SaharVahdati ! We'll present the work at #ACL2024 in Bangkok this year where I hope I'll be able to meet a few of you.

    Blog post: linkedin.com/pulse/beyond-boun

    Paper: amazon.science/publications/be

    #AI #LLMs #QuestionAnswering #ConversationalAI