Advertisement ยท 728 ร— 90

Posts by Andreas Vlachos

Excited that our ICML 2026 workshop Statistical Frameworks for Uncertainty in Agentic Systems got accepted ๐ŸŽ‰
@icmlconf.bsky.social
#icml2026

We want to bring together people thinking about uncertainty and agentic systems.

2 weeks ago 3 1 1 0

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...

4 months ago 3 0 0 0
Logo of the Ubiquitous Knowledge Processing (UKP) Lab, featuring a stylized grey and red globe design next to the labโ€™s name in grey capital letters.

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

๐Ÿงญ โ€œ๐—ง๐—ต๐—ฒ ๐—ฝ๐—ฎ๐˜€๐˜, ๐—ฝ๐—ฟ๐—ฒ๐˜€๐—ฒ๐—ป๐˜ ๐—ฎ๐—ป๐—ฑ ๐—ณ๐˜‚๐˜๐˜‚๐—ฟ๐—ฒ ๐—ผ๐—ณ ๐˜๐—ต๐—ฒ ๐—จ๐—ž๐—ฃ ๐—Ÿ๐—ฎ๐—ฏโ€ - ๐—ช๐—ผ๐—ฟ๐—ธ๐˜€๐—ต๐—ผ๐—ฝ ๐—ถ๐—ป ๐—–๐—ฎ๐—บ๐—ฏ๐—ฟ๐—ถ๐—ฑ๐—ด๐—ฒ
Today, members of the international UKP Lab community gather in Cambridge to reflect on the Labโ€™s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research.

(1/๐Ÿงต)

5 months ago 4 1 1 0
Image of audience at ORIGen workshop @ COLM 2025

Image of audience at ORIGen workshop @ COLM 2025

Andreas Vlachos answers audience questions at ORIGen @ COLM 2025

Andreas Vlachos answers audience questions at ORIGen @ COLM 2025

Malihe Alikhani delivers keynote address at ORIGen @ COLM 2025

Malihe Alikhani delivers keynote address at ORIGen @ COLM 2025

Organizers and participants at ORIGen @ COLM 2025

Organizers and participants at ORIGen @ COLM 2025

And that's a wrap! Thanks to everyone who helped make the first ORIGen workshop a success! @andreasvlachos.bsky.social @malihealikhani.bsky.social @qveraliao.bsky.social #COLM2025 #AI #NLP #LLMs

6 months ago 5 1 0 0
Community Notes require a Community
How we used a novel analysis to understand what causes people to quit the widely adopted content-moderation system

Community Notes require a Community How we used a novel analysis to understand what causes people to quit the widely adopted content-moderation system

New newsletter! Understanding participation in the X Community Notes system, via my love of data visualisation and stronger causal inference methods!

#DataViz #CausalInference #FactChecking #CommunityNotes

open.substack.com/pub/tomstafford/p/commun...

6 months ago 1 4 0 0

remember to submit papers on topics related to fact-checking, including the previous shared tasks on AVERITEC, FEVEROUS and FEVER. Deadline 6th of October (ARR) and 19th of December (direct submissions). Get keen!

6 months ago 2 0 0 0
Fact Extraction and VERification

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...

6 months ago 3 0 1 1
Invited speaker Andreas Vlachos of the University of Cambridge

Invited speaker Andreas Vlachos of the University of Cambridge

We are excited to welcome @andreasvlachos.bsky.social to ORIGen @ @colmweb.org for his invited talk "Toward Constructive Conversations"! #LLMs #AI #NLP #HCI

7 months ago 6 2 0 0

Many thanks for inviting me!

8 months ago 1 0 0 0
Advertisement

Looking forward to this year's edition! With great speakers: Ryan McDonald Yulan He @vn-ml.bsky.social @antonisa.bsky.social Raquel Fernandez @annarogers.bsky.social Preslav Nakov @mohitbansal.bsky.social @eunsol.bsky.social Marie-Catherine de Marnefffe !

10 months ago 6 3 0 0
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.

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.

A string may get 17 times less probability if tokenised as two symbols (e.g., โŸจhe, lloโŸฉ) than as one (e.g., โŸจhelloโŸฉ)โ€”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!

10 months ago 53 9 1 3
Post image

๐Ÿ“ฃ Call for Participation EXTENDED to Sunday 15 June for the #AthNLP2025 !
๐Ÿ“ 4โ€“10 September 2025 | NCSR Demokritos, Athens
๐Ÿ“„ Apply & view the full program: athnlp.github.io/2025/cfp.html

#NLP #AI #SummerSchool #NaturalLanguageProcessing

10 months ago 3 3 0 0
Post image

๐Ÿ“ข CFP announced for the Athens #NaturalLanguageProcessing #SummerSchool!
Are you passionate about #NLP and #MachineLearning?
Join us in Athens 4โ€“10 Sept at NCSR Demokritos
for talks, hands-on labs & top domain experts!
๐Ÿ“…Apply by 30 May!
athnlp.github.io/2025/cfp.html
#AthNLP2025 #AI

11 months ago 2 1 0 1
Fact Extraction and VERification

The call for papers for the 8th FEVER workshop at #ACL is out: fever.ai/workshop.html Deadline for is on May 19th! And if you have a paper already reviewed in ARR, you can commit it until June 9th!

11 months ago 0 0 0 0
Post image Post image

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.

11 months ago 7 2 1 0

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

11 months ago 2 1 0 0
Fact Extraction and VERification

Pleased to announce the next
FEVER workshop
at ACL2025! Regular workshop papers (ARR and direct submissions) due 15th of April! And new shared task focusing on reproducible and efficient verification of real world claims! Check fever.ai and get keen!

1 year ago 4 1 0 0

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

1 year ago 7 2 0 0

Happy to announce that our work "A Bayesian Optimization Approach to Machine Translation" was accepted to NAACL 2025!

Special thanks to @ufal-cuni.bsky.social for organizing MT Marathon 2025 where I was able to team up with @maikezufle.bsky.social and @zouharvi.bsky.social !

Explainer below:

1 year ago 11 2 1 1
Advertisement
group of Ukrainian students holding up the Ukrainian national flag

group of Ukrainian students holding up the Ukrainian national flag

Griffin Scholars (very smart Ukrainian undergraduates from top unis) are looking for research internships in maths or CS.

(many of them can't return to Ukraine for the summer).

If you can host them (we may help with funding), please fill out this form:

ferenchuszar1.typeform.com/to/WjXursg3

1 year ago 11 4 0 0