Tomorrow is the day! We cannot wait to see you at #ACL2024 ACL 2025 Knowledgeable LMs workshop! Super excited for keynotes by Peter Clark Luke Zettlemoyer Tatsunori Hashimoto Isabelle Augenstein Eduard Hovy Hannah Rashkin! Will announce a Best Paper Award ($500) and a Outstanding Paper

About to give my keynote on “Quantifying Societal Biases Towards Entities” — come join us in World Ballroom B! #ACL2024 #ACL2024NLP #NLProc

Time for the first Keynote from Isabelle Augenstein at genderbiasnlp! #ACL2024

A good reminder for those of us in LLM land (like me) that we don't only need to mitigate gender biases *caused* by LM generation, but we should enable researchers to *use* LMs to discover biases in human content. From Isabelle Augenstein's keynote genderbiasnlp #ACL2024

Our afternoon session is ongoing with wonderful speakers Isabelle Augenstein Eduard Hovy @HannahRashkin and a panel discussion on hot takes of Knowledge + LLMs! #ACL2024 Lotus Room 10 (Zoom: underline.io/events/466/ses…)

Excellent talk by Eduard Hovy at the #ACL2024 KnowLLM workshop providing an overview of problems involving knowledge in LLMs: control vs. declarative vs. procedural knowledge, requiring different approaches. #ACL2024NLP #NLProc

Good to be at #ACL2024 ! See you again (hopefully)🤞

It was to catch up with everyone #ACL2024 & get inspiration for future research 💡 Kudos to the organisers for planning a fantastic social event too (Sara Vera Marjanović’s happy face meeting the Thai boxing champion post-match says it all 😂) 👏 See you again at #EMNLP2024! #NLProc

Thanks to everyone who was interested in discussing our research #acl2024! Finally uploaded the slides of my invited talks at the Knowledgeable LM & Gender Bias in #NLProc workshops; find them here: isabelleaugenstein.github.io/talks.html #acl2024nlp Manling Li genderbiasnlp Seraphina Goldfarb-Tarrant

LLMs are changing the game - but at what cost? Our perspective paper in Nature Machine Intelligence reveals how AI “hallucinations” can spread misinformation. Discover the truth about keeping AI honest. Paper: rdcu.be/dRFy0 🔍🤖 #AI #LLM #FactChecking #Misinformation #TechEthics

So proud of Pepa Atanasova for starting as faculty DIKU - Department of Computer Science, UCPH today! She is a rising star in #NLProc #XAI, having won both an ELLIS & Informatics Europe PhD award. We're beyond fortunate to have her stay on CopeNLU. Looking forward to the continued collaborations! 👏

From AI2 to P1... first day in my new office in Copenhagen! 🔭 I'll be at the Pioneer Centre for AI for one year to work on narratives+AI research with Serge Belongie and Isabelle Augenstein. Very excited to make new connections; please say hi if you're local or nearby!

Last week, our group went on a research retreat in idyllic surroundings in Southern Sweden. We did orienteering in the forest, cooked together, did yoga, worked on a group project, and more ☺️🌳🍄🍕🧘‍♀️🧑‍💻

Super excited to share that our paper "Social Bias Probing: Fairness Benchmarking for LMs" has been accepted at the main track of #EMNLP2024 🎉 Work done with the amazing Karolina Stanczak Isabelle Augenstein Riccardo Guidotti from CopeNLU & KDD Lab Pisa 🔗 arxiv.org/pdf/2311.09090 A short thread:

And not only did she defend her PhD with flying colours, but star PhD alumna Karolina Stanczak also won UCPH SCIENCE's PhD award! 🤩 🥳👏 DIKU - Department of Computer Science, UCPH #NLProc x.com/IAugenstein/st…

Huge congratulations to Karolina Stanczak who has been awarded the SCIENCE Faculty's PhD Award 2024 for her outstanding thesis! 🌟🎉 Karolina has advanced new techniques to detect linguistic and societal biases in language models. Well done, Karolina! #NLProc SCIENCE - KU Isabelle Augenstein

Excited to welcome my former colleague Dirk Hovy back to DIKU - Department of Computer Science, UCPH Pioneer Centre for AI for a talk on why language models do not understand language aicentre.dk/events/talk-on… #NLProc

🚨New Benchmark Alert🚨 Our paper accepted to Findings of EMNLP 2024🌴 introduces a new dataset, DynamicQA! DynamicQA contains inherently conflicting data (both disputable🤷‍♀️ & temporal🕰️) crucial to studying LM’s internal memory conflict. Work with Haeun Yu 🥳 #EMNLP2024 #NLProc

🌊 Sail with us at #WiNLP2024! 🌊 Join panel "Sailing the NLP Seas: Navigating Research in the Age of LLMs" on Nov 15, 11:00 AM - 12:00 PM with Abhilasha Ravichander, @Sunayana , Isabelle Augenstein, Lu Wang, Mrinmaya Sachan will dive into the evolving tides of NLP in the LLM era. ⚓️ #EMNLP2024

👋Psst! Want more faithful, verifiable and robust #LLM reasoning than with CoT, but using external solvers is meh? Our FLARE💫uses Logic Programming with Exhaustive Simulated Search to achieve this.🧵 With Pasquale Minervini Patrick Lewis Pat Verga Isabelle Augenstein arxiv.org/abs/2410.11900