For our last Thursday Reading Group, @taniseceron.bsky.social presented "Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback" by A. D. Lindström et al. (2025)
Paper: link.springer.com/article/10.1...
#NLProc
Paper: link.springer.com/article/10.1...
#NLProc
October 28, 2025 at 10:43 AM
Everybody can reply
1 reposts
5 likes
#MemoryModay #NLProc 'Dense Node Representation for Geolocation' by Fornaciari & @dirkhovy.bsky.social reveals efficient geolocation methods using node2vec & doc2vec models. Greater network size, less parameters.
Dense Node Representation for Geolocation
Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
aclanthology.org
October 27, 2025 at 4:06 PM
Everybody can reply
2 reposts
3 likes
⏲️ 🎓 Only a few days left to apply to do a PhD in Natural Language Processing with @apepa.bsky.social and me @copenlu.bsky.social @aicentre.dk!
#NLProc #ML #XAI #phdpositions #academicjobs
#NLProc #ML #XAI #phdpositions #academicjobs
Looking for PhD opportunites in #NLProc #XAI? We @copenlu.bsky.social @aicentre.dk @apepa.bsky.social are hiring for a start in Spring or Autumn 2026.
📆 Application deadline: 31 October 2025
ℹ️ Details: www.copenlu.com/news/phd-fel...
👀 Reasons to apply: www.copenlu.com/post/why-ucph/
📆 Application deadline: 31 October 2025
ℹ️ Details: www.copenlu.com/news/phd-fel...
👀 Reasons to apply: www.copenlu.com/post/why-ucph/
PhD fellowships for start in Spring or Autumn 2026 | CopeNLU
Would you like to join our lab as a PhD student in 2026? We have several openings. Read more about reasons to join CopeNLU here.
Start in Spring 2026 We have two fully funded 3-year PhD fellowships av...
www.copenlu.com
October 27, 2025 at 1:16 PM
Everybody can reply
1 reposts
4 likes
1 saves
🚨 SECOND CALL FOR SYSTEM DEMONSTRATIONS 🚨
Bring your best technology demos to Rabat, Morocco 🇲🇦, Mar 24-29 2026
👉 Paper submission deadline: 1 December 2025
Details: 2026.eacl.org/calls/demos/
#NLProc #EACL2026
Bring your best technology demos to Rabat, Morocco 🇲🇦, Mar 24-29 2026
👉 Paper submission deadline: 1 December 2025
Details: 2026.eacl.org/calls/demos/
#NLProc #EACL2026
Call for System Demonstrations
Official website for the 2026 Conference of the European Chapter of the Association for Computational Linguistics
2026.eacl.org
October 27, 2025 at 9:58 AM
Everybody can reply
1 likes
OpenEuroLLM completing 2 days of sharing progress and next steps pursuing the goal of developing strong multilingual foundation models aligned with European strategic vision & standards.
Gathering at BSC nearby MareNostrum 5 supercomputer made us feel home.
#Barcelona #NLProc #OpenEuroLLM
Gathering at BSC nearby MareNostrum 5 supercomputer made us feel home.
#Barcelona #NLProc #OpenEuroLLM
October 24, 2025 at 1:49 PM
Everybody can reply
1 reposts
3 likes
Let’s present the tasks at #EVALITA2026!
Last but not least: FadeIT 🔍💬
Can your system spot fallacies in social media posts?
FadeIT focuses on Italian texts about migration, climate change & public health.
Detect flawed reasoning — where it spreads fastest.
#NLProc
Last but not least: FadeIT 🔍💬
Can your system spot fallacies in social media posts?
FadeIT focuses on Italian texts about migration, climate change & public health.
Detect flawed reasoning — where it spreads fastest.
#NLProc
October 24, 2025 at 7:24 AM
Everybody can reply
Let’s present the tasks at #EVALITA2026!
Tenth up: PFB – Prometeia Financial Benchmark 💶📊
Can LLMs handle finance?
PFB evaluates open & closed models on domain-specific MCQs, with a twist: each question has a complexity score.
2 tasks: Italian and Multilingual QA
From GPT to finance pro.
#NLProc
Tenth up: PFB – Prometeia Financial Benchmark 💶📊
Can LLMs handle finance?
PFB evaluates open & closed models on domain-specific MCQs, with a twist: each question has a complexity score.
2 tasks: Italian and Multilingual QA
From GPT to finance pro.
#NLProc
October 22, 2025 at 8:38 AM
Everybody can reply
1 likes
The #emnlp2025 conference is starting in two weeks in Suzhou, #china.
Language Technology Group #oslo will be there with at least four papers, see the thread🧵 :
#nlproc
Language Technology Group #oslo will be there with at least four papers, see the thread🧵 :
#nlproc
October 20, 2025 at 4:23 PM
Everybody can reply
#MemoryModay #NLProc 'Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection' - Attanasio et al. Explores reliability of interpretability in hate speech detection.
Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
Giuseppe Attanasio, Debora Nozza, Eliana Pastor, Dirk Hovy. Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP. 2022.
aclanthology.org
October 20, 2025 at 3:23 PM
Everybody can reply
3 reposts
4 likes
There’s still time to join our Cruciverb-IT shared task! 🧩
📂 Data available here: huggingface.co/datasets/cru...
🌐 Website: sites.google.com/view/crucive...
#NLProc
📂 Data available here: huggingface.co/datasets/cru...
🌐 Website: sites.google.com/view/crucive...
#NLProc
Let’s present the tasks at #EVALITA2026!
Ninth up: Cruciverb-IT 🧩🇮🇹
Ready to crack some Italian crosswords?
Cruciverb-IT offers a challenging playground for NLP systems:
1️⃣ Answer clues from real crosswords
2️⃣ Autonomously solve full crossword grids
Wordplay meets AI.
#NLProc
Ninth up: Cruciverb-IT 🧩🇮🇹
Ready to crack some Italian crosswords?
Cruciverb-IT offers a challenging playground for NLP systems:
1️⃣ Answer clues from real crosswords
2️⃣ Autonomously solve full crossword grids
Wordplay meets AI.
#NLProc
October 20, 2025 at 1:28 PM
Everybody can reply
It was a pleasure to have @rochellechoenni.bsky.social presenting "Brittle but Steerable: Aligning Cultural Values in Multilingual Language Models" at our lab seminar.
#NLProc
#NLProc
October 20, 2025 at 12:38 PM
Everybody can reply
1 reposts
7 likes
2 saves
📅 Oct 27–31 Taught entirely in English, the course consists of 20 hours of live online sessions, spread across these 5 afternoons.
ℹ️ More information: www.hitz.eus/gpllmme/
⚠️ Fill out the form to register: www.hitz.eus/events/train...
#AI_LT_catedra #AI #nlproc
ℹ️ More information: www.hitz.eus/gpllmme/
⚠️ Fill out the form to register: www.hitz.eus/events/train...
#AI_LT_catedra #AI #nlproc
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
October 20, 2025 at 10:08 AM
Everybody can reply
1 likes
Let’s present the tasks at #EVALITA2026!
Ninth up: Cruciverb-IT 🧩🇮🇹
Ready to crack some Italian crosswords?
Cruciverb-IT offers a challenging playground for NLP systems:
1️⃣ Answer clues from real crosswords
2️⃣ Autonomously solve full crossword grids
Wordplay meets AI.
#NLProc
Ninth up: Cruciverb-IT 🧩🇮🇹
Ready to crack some Italian crosswords?
Cruciverb-IT offers a challenging playground for NLP systems:
1️⃣ Answer clues from real crosswords
2️⃣ Autonomously solve full crossword grids
Wordplay meets AI.
#NLProc
October 20, 2025 at 8:38 AM
Everybody can reply
1 quotes
1 likes
Let’s present the tasks at #EVALITA2026!
Eighth up: SVELA 🧠🧽
Can LLMs forget on purpose?
SVELA tackles Machine Unlearning: design and evaluate metrics to verify if a model forgets specific knowledge while keeping the rest intact.
Selective forgetting, measurable impact.
#NLProc
Eighth up: SVELA 🧠🧽
Can LLMs forget on purpose?
SVELA tackles Machine Unlearning: design and evaluate metrics to verify if a model forgets specific knowledge while keeping the rest intact.
Selective forgetting, measurable impact.
#NLProc
October 17, 2025 at 11:14 AM
Everybody can reply
#wassa, one of the most established #nlproc workshops in sentiment, subjectivity, emotions is coming back in 2026. We'd love to see your new work on the topic in Rabat next year.
#WASSA2026 the Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, will be held at #EACL2026
Organizers: @jeremy-nlp.bsky.social , Valentin Barriere, Orphée De Clercq, @romanklinger.de, @deboranozza.bsky.social , @celianri.bsky.social , and Pranaydeep Singh
Organizers: @jeremy-nlp.bsky.social , Valentin Barriere, Orphée De Clercq, @romanklinger.de, @deboranozza.bsky.social , @celianri.bsky.social , and Pranaydeep Singh
October 16, 2025 at 9:49 PM
Everybody can reply
4 reposts
9 likes
#TBT #NLProc 'Geolocation with Attention-Based Multitask Learning Models' by Tommaso Fornaciari, @dirkhovy.bsky.social (2019) reveals how online political talks can become one-sided. #SocialMedia
Geolocation with Attention-Based Multitask Learning Models
Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
aclanthology.org
October 16, 2025 at 3:04 PM
Everybody can reply
2 reposts
4 likes
📣 LLM-as-a-qualitative-judge: automating error analysis in natural language generation
TLDR: our approach outputs a summary of error types and their counts in an NLP system
📜 Paper: arxiv.org/abs/2506.09147
💻 Code to try it on your task: github.com/tunde-ajayi/...
#NLProc #LLM
TLDR: our approach outputs a summary of error types and their counts in an NLP system
📜 Paper: arxiv.org/abs/2506.09147
💻 Code to try it on your task: github.com/tunde-ajayi/...
#NLProc #LLM
October 16, 2025 at 10:44 AM
Everybody can reply
1 saves
The second edition of LoResLM will take place in Rabat, Morocco, alongside @eaclmeeting.bsky.social 2026. #NLProc #EACL2026 #LoResLM
The second edition of LoResLM will take place in Rabat, Morocco, alongside @eaclmeeting.bsky.social 2026.
Hansi Hettiarachchi | @tharindudr.bsky.social | @aplum.bsky.social | @perayson.bsky.social | Ruslan Mitkov | Mohamed Medhat Gaber | Damith Premasiri | Fiona Anting Tan | Lasitha Uyangodage
Hansi Hettiarachchi | @tharindudr.bsky.social | @aplum.bsky.social | @perayson.bsky.social | Ruslan Mitkov | Mohamed Medhat Gaber | Damith Premasiri | Fiona Anting Tan | Lasitha Uyangodage
October 15, 2025 at 12:49 PM
Everybody can reply
⏰ The deadline to submit tutorial proposals for EACL'26 & ACL'26 is approaching!
Submission deadline: October 20, 2025
More info: aclweb.org/portal/conte...
#NLProc #ACL2026NLP #EACL2026
Submission deadline: October 20, 2025
More info: aclweb.org/portal/conte...
#NLProc #ACL2026NLP #EACL2026
Joint Call for Tutorial Proposals (EACL/ACL) 2026 | ACL Member Portal
aclweb.org
October 14, 2025 at 8:56 AM
Everybody can reply
2 reposts
5 likes
1 saves
#MemoryModay #NLProc ' 'State of Profanity Obfuscation in NLP Scientific Publications' probes bias in non-English papers. @debora_nozza & Dirk Hovy (2023) propose 'PrOf' to aid authors & improve access. aclanthology.org/2023.finding...
The State of Profanity Obfuscation in Natural Language Processing Scientific Publications
Debora Nozza, Dirk Hovy. Findings of the Association for Computational Linguistics: ACL 2023. 2023.
aclanthology.org
October 13, 2025 at 3:05 PM
Everybody can reply
2 reposts
4 likes
Thanks Clara Meister for presenting "Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization" at our lab seminar.
#NLProc #tokenization #fairness
#NLProc #tokenization #fairness
October 10, 2025 at 3:05 PM
Everybody can reply
1 reposts
5 likes
🔍 Im November veranstalten wir ein eintägiges Kolloquium zur Autorschaftsanalyse: https://staff.germanistik.rub.de/kolloquium-autorschaftsanalyse/
Die Anmeldung ist noch bis 30.10. möglich!
Boost erwünscht 🙏
#linguistik #variation #autorschaft #nlproc
Die Anmeldung ist noch bis 30.10. möglich!
Boost erwünscht 🙏
#linguistik #variation #autorschaft #nlproc
October 10, 2025 at 11:05 AM
Everybody can reply
5 reposts
2 likes
#TBT #NLProc "Explaining Speech Classification Models" by Pastor et al. (2024) makes speech classification more transparent! 🔍 Their research reveals which words matter most and how tone and background noise impact decisions.
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio, Dirk Hovy, Elena Baralis. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long...
aclanthology.org
October 9, 2025 at 3:05 PM
Everybody can reply
3 reposts
5 likes