Andreas Vlachos

@andreasvlachos.bsky.social

website: https://t.co/ml5yPJjZLO Natural Language Processing and Machine Learning researcher at the University of Cambridge. Member of the PaNLP group: https://www.panlp.org/ and fellow of Fitzwilliam College.

Results for the shared task now publicly available (huggingface.co/spaces/FEVER...) Lot's of progress compared to our baseline, a lot left to do! Reminder to submit your #FactChecking papers to the #EACL2026 @FEVERworkshop by 19/12 here: openreview.net/group?id=eac...

Bild
Andreas Vlachos@andreasvlachos.bsky.social · 10mo ago

Excited to announce the 9th @FEVERworkshop collocated with #EACL2026 in Morocco: fever.ai/index.html with a new shared task on #factchecking image-text claims with evidence from the web using the AVerImaTeC dataset: arxiv.org/abs/2505.17978 Deadline 2nd of December! And...

🧭 “𝗧𝗵𝗲 𝗽𝗮𝘀𝘁, 𝗽𝗿𝗲𝘀𝗲𝗻𝘁 𝗮𝗻𝗱 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗨𝗞𝗣 𝗟𝗮𝗯” - 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗶𝗻 𝗖𝗮𝗺𝗯𝗿𝗶𝗱𝗴𝗲 Today, members of the international UKP Lab community gather in Cambridge to reflect on the Lab’s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research. (1/🧵)

Logo of the Ubiquitous Knowledge Processing (UKP) Lab, featuring a stylized grey and red globe design next to the lab’s name in grey capital letters.

A string may get 17 times less probability if tokenised as two symbols (e.g., ⟨he, llo⟩) than as one (e.g., ⟨hello⟩)—by an LM trained from scratch in each situation! Our new ACL paper proposes an observational method to estimate this causal effect! Longer thread soon!

Title of paper "Causal Estimation of Tokenisation Bias" and schematic of how we define tokenisation bias, which is the causal effect we are interested in.

Being in a hot air balloon in Albuquerque really makes one ponder *how to efficiently pick the best translation candidate without running expensive evaluation metrics on all of them.* See you tomorrow at 9:00 in Hall 3 #NAACL2025.

BildBild

Honoured to receive this award! Tagging @pietrolesci.bsky.social and @tpimentel.bsky.social !

Cambridge Computer Science@cst.cam.ac.uk · last yr.

🎉 Congratulations @pietrolesci.bsky.social, Clara Meister, Thomas Hofmann, @andreasvlachos.bsky.social & Tiago Pimentel! They won Publication of the Year at our annual Hall of Fame awards last week for their paper on 'Causal Estimation of Memorisation Profiles'. www.cst.cam.ac.uk/announcing-w...

Andreas Vlachos, our Professor of Natural Language Processing and Machine Learning, collected the award from Head of Department Alastair Beresford at our Hall of Fame Awards ceremony on 23 April 2025.

The First Workshop on Large Language Model Memorization will be co-located at @aclmeeting.bsky.social in Vienna. Help us spread the word!

The First Workshop on Large Language Model Memorization (L2M2)@l2m2workshop.bsky.social · 2y ago

📢 The First Workshop on Large Language Model Memorization (L2M2) will be co-located with @aclmeeting.bsky.social in Vienna 🎉 💡 L2M2 brings together researchers to explore memorization from multiple angles. Whether it's text-only LLMs or Vision-language models, we want to hear from you! 🌍