Ondrej Dusek
@tuetschek.bsky.social
Teaching computers to talk at Charles University. (Computational) linguistics, politics, climate, public transit. He/him.
Reposted by Ondrej Dusek
🔤 Pretraining Language Models with LoRA and Artificial Languages
Nalin Kumar, Mateusz Lango, @tuetschek.bsky.social t
aclanthology.org/2025.babylm-...
Constructed artificial languages with LoRA affects language model development.
Nalin Kumar, Mateusz Lango, @tuetschek.bsky.social t
aclanthology.org/2025.babylm-...
Constructed artificial languages with LoRA affects language model development.
Pretraining Language Models with LoRA and Artificial Languages
Nalin Kumar, Mateusz Lango, Ondrej Dusek. Proceedings of the First BabyLM Workshop. 2025.
aclanthology.org
November 11, 2025 at 2:37 PM
🔤 Pretraining Language Models with LoRA and Artificial Languages
Nalin Kumar, Mateusz Lango, @tuetschek.bsky.social t
aclanthology.org/2025.babylm-...
Constructed artificial languages with LoRA affects language model development.
Nalin Kumar, Mateusz Lango, @tuetschek.bsky.social t
aclanthology.org/2025.babylm-...
Constructed artificial languages with LoRA affects language model development.
Reposted by Ondrej Dusek
🎓 You are an LLM teaching a smaller model everything you know: Multi-task pretraining of language models with LLM-designed study plans
Wiktor Kamzela, Mateusz Lango, @tuetschek.bsky.social
aclanthology.org/2025.babylm-...
Wiktor Kamzela, Mateusz Lango, @tuetschek.bsky.social
aclanthology.org/2025.babylm-...
You are an LLM teaching a smaller model everything you know: Multi-task pretraining of language models with LLM-designed study plans
Wiktor Kamzela, Mateusz Lango, Ondrej Dusek. Proceedings of the First BabyLM Workshop. 2025.
aclanthology.org
November 11, 2025 at 2:37 PM
🎓 You are an LLM teaching a smaller model everything you know: Multi-task pretraining of language models with LLM-designed study plans
Wiktor Kamzela, Mateusz Lango, @tuetschek.bsky.social
aclanthology.org/2025.babylm-...
Wiktor Kamzela, Mateusz Lango, @tuetschek.bsky.social
aclanthology.org/2025.babylm-...
Reposted by Ondrej Dusek
📚 SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
November 7, 2025 at 8:54 PM
📚 SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Reposted by Ondrej Dusek
🤖 LLM Agents Implement an NLG System from Scratch
Mateusz Lango, Ondrej Dusek
aclanthology.org/2025.emnlp-i...
LLM agents can autonomously build interpretable, rule-based RDF-to-text generators from scratch, combining the LLMs with the transparency and reliability of traditional rule-based systems.
Mateusz Lango, Ondrej Dusek
aclanthology.org/2025.emnlp-i...
LLM agents can autonomously build interpretable, rule-based RDF-to-text generators from scratch, combining the LLMs with the transparency and reliability of traditional rule-based systems.
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
Mateusz Lango, Ondrej Dusek. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
aclanthology.org
November 7, 2025 at 8:54 PM
🤖 LLM Agents Implement an NLG System from Scratch
Mateusz Lango, Ondrej Dusek
aclanthology.org/2025.emnlp-i...
LLM agents can autonomously build interpretable, rule-based RDF-to-text generators from scratch, combining the LLMs with the transparency and reliability of traditional rule-based systems.
Mateusz Lango, Ondrej Dusek
aclanthology.org/2025.emnlp-i...
LLM agents can autonomously build interpretable, rule-based RDF-to-text generators from scratch, combining the LLMs with the transparency and reliability of traditional rule-based systems.
Reposted by Ondrej Dusek
👥 Can Large Language Models Personalize Dialogues to Generational Styles?
P. Balestrucci, @tuetschek.bsky.social, L. Anselma, A. Mazzei
aclanthology.org/2025.finding...
Can LLMs adapt dialogues to generational styles? We show with P-MultiWoZ that models capture patterns from Boomers to Gen Z.
P. Balestrucci, @tuetschek.bsky.social, L. Anselma, A. Mazzei
aclanthology.org/2025.finding...
Can LLMs adapt dialogues to generational styles? We show with P-MultiWoZ that models capture patterns from Boomers to Gen Z.
Can Large Language Models Personalize Dialogues to Generational Styles?
Pier Felice Balestrucci, Ondrej Dusek, Luca Anselma, Alessandro Mazzei. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
aclanthology.org
November 7, 2025 at 8:54 PM
👥 Can Large Language Models Personalize Dialogues to Generational Styles?
P. Balestrucci, @tuetschek.bsky.social, L. Anselma, A. Mazzei
aclanthology.org/2025.finding...
Can LLMs adapt dialogues to generational styles? We show with P-MultiWoZ that models capture patterns from Boomers to Gen Z.
P. Balestrucci, @tuetschek.bsky.social, L. Anselma, A. Mazzei
aclanthology.org/2025.finding...
Can LLMs adapt dialogues to generational styles? We show with P-MultiWoZ that models capture patterns from Boomers to Gen Z.
Reposted by Ondrej Dusek
📊 Real-World Summarization: When Evaluation Reaches Its Limits
@patuchen.bsky.social , @tuetschek.bsky.social , @saad.me.uk
aclanthology.org/2025.finding...
For hotel highlights, metrics like word overlap surprisingly match human judgments better than complex methods. LLMs unreliable as evaluators.
@patuchen.bsky.social , @tuetschek.bsky.social , @saad.me.uk
aclanthology.org/2025.finding...
For hotel highlights, metrics like word overlap surprisingly match human judgments better than complex methods. LLMs unreliable as evaluators.
Real-World Summarization: When Evaluation Reaches Its Limits
Patrícia Schmidtová, Ondrej Dusek, Saad Mahamood. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
aclanthology.org
November 7, 2025 at 8:54 PM
📊 Real-World Summarization: When Evaluation Reaches Its Limits
@patuchen.bsky.social , @tuetschek.bsky.social , @saad.me.uk
aclanthology.org/2025.finding...
For hotel highlights, metrics like word overlap surprisingly match human judgments better than complex methods. LLMs unreliable as evaluators.
@patuchen.bsky.social , @tuetschek.bsky.social , @saad.me.uk
aclanthology.org/2025.finding...
For hotel highlights, metrics like word overlap surprisingly match human judgments better than complex methods. LLMs unreliable as evaluators.
Reposted by Ondrej Dusek
Reposted by Ondrej Dusek
The registration page for #INLG2025 is now live! Join us in Vietnam at the Oct 29 - Nov 2 for the best conference on #NaturalLanguageGeneration
2025.inlgmeeting.org/registration...
Curious to see what will be presented? Check out this list of accepted papers! 2025.inlgmeeting.org/accepted-pap...
2025.inlgmeeting.org/registration...
Curious to see what will be presented? Check out this list of accepted papers! 2025.inlgmeeting.org/accepted-pap...
September 16, 2025 at 12:15 PM
The registration page for #INLG2025 is now live! Join us in Vietnam at the Oct 29 - Nov 2 for the best conference on #NaturalLanguageGeneration
2025.inlgmeeting.org/registration...
Curious to see what will be presented? Check out this list of accepted papers! 2025.inlgmeeting.org/accepted-pap...
2025.inlgmeeting.org/registration...
Curious to see what will be presented? Check out this list of accepted papers! 2025.inlgmeeting.org/accepted-pap...
Reposted by Ondrej Dusek
Check out the slides from our SCAI'2025 #convsearch workshop collocated with @ijcai.org #IJCAI2025 on LLMs, retrieval & QA, recommendations, negotiations, evaluation and transparency
scai.info/scai-2025
@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social
scai.info/scai-2025
@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social
SCAI 2025
Online Event on Search-Oriented Conversational AI.
scai.info
September 9, 2025 at 10:34 AM
Check out the slides from our SCAI'2025 #convsearch workshop collocated with @ijcai.org #IJCAI2025 on LLMs, retrieval & QA, recommendations, negotiations, evaluation and transparency
scai.info/scai-2025
@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social
scai.info/scai-2025
@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social
Reposted by Ondrej Dusek
Our paper "OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs" has been accepted to #INLG2025 conference!
You can read the preprint here: arxiv.org/abs/2503.11858
You can read the preprint here: arxiv.org/abs/2503.11858
August 23, 2025 at 4:36 PM
Our paper "OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs" has been accepted to #INLG2025 conference!
You can read the preprint here: arxiv.org/abs/2503.11858
You can read the preprint here: arxiv.org/abs/2503.11858
Reposted by Ondrej Dusek
FreshTab: Sourcing Fresh Resources for Table-to-Text Generation Evaluation
by @navitas.bsky.social, @oplatek.bsky.social, @zdenekkasner.bsky.social, @tuetschek.bsky.social .bsky.social
by @navitas.bsky.social, @oplatek.bsky.social, @zdenekkasner.bsky.social, @tuetschek.bsky.social .bsky.social
July 31, 2025 at 1:30 PM
FreshTab: Sourcing Fresh Resources for Table-to-Text Generation Evaluation
by @navitas.bsky.social, @oplatek.bsky.social, @zdenekkasner.bsky.social, @tuetschek.bsky.social .bsky.social
by @navitas.bsky.social, @oplatek.bsky.social, @zdenekkasner.bsky.social, @tuetschek.bsky.social .bsky.social
Reposted by Ondrej Dusek
ReproHum #0669-08: Reproducing Sentiment Transfer Evaluation
by @navitas.bsky.social, M. Lango, @patuchen.bsky.social, @tuetschek.bsky.social
Challenge to reproduce human evaluations from NLP papers, testing the reproducibility of evaluation studies
by @navitas.bsky.social, M. Lango, @patuchen.bsky.social, @tuetschek.bsky.social
Challenge to reproduce human evaluations from NLP papers, testing the reproducibility of evaluation studies
July 31, 2025 at 1:30 PM
ReproHum #0669-08: Reproducing Sentiment Transfer Evaluation
by @navitas.bsky.social, M. Lango, @patuchen.bsky.social, @tuetschek.bsky.social
Challenge to reproduce human evaluations from NLP papers, testing the reproducibility of evaluation studies
by @navitas.bsky.social, M. Lango, @patuchen.bsky.social, @tuetschek.bsky.social
Challenge to reproduce human evaluations from NLP papers, testing the reproducibility of evaluation studies
Reposted by Ondrej Dusek
OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs
by @ivankartac.bsky.social, M. Lango, @tuetschek.bsky.social
arxiv.org/abs/2503.11858
Open-source NLG evaluation metric that explains errors and matches human judgments without proprietary models
by @ivankartac.bsky.social, M. Lango, @tuetschek.bsky.social
arxiv.org/abs/2503.11858
Open-source NLG evaluation metric that explains errors and matches human judgments without proprietary models
July 31, 2025 at 1:30 PM
OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs
by @ivankartac.bsky.social, M. Lango, @tuetschek.bsky.social
arxiv.org/abs/2503.11858
Open-source NLG evaluation metric that explains errors and matches human judgments without proprietary models
by @ivankartac.bsky.social, M. Lango, @tuetschek.bsky.social
arxiv.org/abs/2503.11858
Open-source NLG evaluation metric that explains errors and matches human judgments without proprietary models
Reposted by Ondrej Dusek
#ACL2025NLP in Vienna 🇦🇹 starts today with 23 🤯 @ufal-cuni.bsky.social folks presenting their work both at the main conference and workshops. Check out our main conference papers today and on Wednesday 👇
July 28, 2025 at 7:27 AM
#ACL2025NLP in Vienna 🇦🇹 starts today with 23 🤯 @ufal-cuni.bsky.social folks presenting their work both at the main conference and workshops. Check out our main conference papers today and on Wednesday 👇
Reposted by Ondrej Dusek
ICML found hidden prompts in accepted papers. They have released a statement icml.cc/Conferences/...
Yes, it’s unacceptable. So is using an LLM to review a paper. Peer review is so broken.
Yes, it’s unacceptable. So is using an LLM to review a paper. Peer review is so broken.
July 24, 2025 at 1:44 AM
ICML found hidden prompts in accepted papers. They have released a statement icml.cc/Conferences/...
Yes, it’s unacceptable. So is using an LLM to review a paper. Peer review is so broken.
Yes, it’s unacceptable. So is using an LLM to review a paper. Peer review is so broken.
Reposted by Ondrej Dusek
#Eurovision is tonight, and here's a hilarious fun fact about it: Israel has started a massive offensive against civilian populations in Gaza with the explicit aim of conquering the entire territory and ethnically cleansing its population, and Eurovision has aggressively refused to give a shit.
May 17, 2025 at 10:48 PM
#Eurovision is tonight, and here's a hilarious fun fact about it: Israel has started a massive offensive against civilian populations in Gaza with the explicit aim of conquering the entire territory and ethnically cleansing its population, and Eurovision has aggressively refused to give a shit.
Reposted by Ondrej Dusek
It is a little weird to me countries aren’t more aggressively, formally trying to take advantage of the U.S. science brain drain. Once in a lifetime opportunity to buy low on Non-Dumbass Americans with PhDs who just wanna look into microscopes and quietly cure ass cancer as our country eats shit.
May 4, 2025 at 8:54 PM
It is a little weird to me countries aren’t more aggressively, formally trying to take advantage of the U.S. science brain drain. Once in a lifetime opportunity to buy low on Non-Dumbass Americans with PhDs who just wanna look into microscopes and quietly cure ass cancer as our country eats shit.
Reposted by Ondrej Dusek
The 👉Machine Learning Prague 2025👈 is happening right now! Today, @patuchen.bsky.social and @navitas.bsky.social presented their posters on text generation with LLMs. Also, don't miss @tuetschek.bsky.social's invited talk tomorrow at 11 a.m.
April 29, 2025 at 2:08 PM
The 👉Machine Learning Prague 2025👈 is happening right now! Today, @patuchen.bsky.social and @navitas.bsky.social presented their posters on text generation with LLMs. Also, don't miss @tuetschek.bsky.social's invited talk tomorrow at 11 a.m.
Reposted by Ondrej Dusek
🚨 NEW WORKSHOP ALERT 🚨
We're thrilled to announce the first-ever Tokenization Workshop (TokShop) at #ICML2025 @icmlconf.bsky.social! 🎉
Submissions are open for work on tokenization across all areas of machine learning.
📅 Submission deadline: May 30, 2025
🔗 tokenization-workshop.github.io
We're thrilled to announce the first-ever Tokenization Workshop (TokShop) at #ICML2025 @icmlconf.bsky.social! 🎉
Submissions are open for work on tokenization across all areas of machine learning.
📅 Submission deadline: May 30, 2025
🔗 tokenization-workshop.github.io
Tokenization Workshop @ ICML 2025
tokenization-workshop.github.io
April 15, 2025 at 5:23 PM
🚨 NEW WORKSHOP ALERT 🚨
We're thrilled to announce the first-ever Tokenization Workshop (TokShop) at #ICML2025 @icmlconf.bsky.social! 🎉
Submissions are open for work on tokenization across all areas of machine learning.
📅 Submission deadline: May 30, 2025
🔗 tokenization-workshop.github.io
We're thrilled to announce the first-ever Tokenization Workshop (TokShop) at #ICML2025 @icmlconf.bsky.social! 🎉
Submissions are open for work on tokenization across all areas of machine learning.
📅 Submission deadline: May 30, 2025
🔗 tokenization-workshop.github.io
Reposted by Ondrej Dusek
“is my calculator horny?“ our tech columnist asks. “i entered 5318008 into it and turned it upside down. what i saw surprised me”
“Can ChatGPT experience joy or suffering? Does Gemini deserve human rights?” our tech columnist asks. “Many A.I. experts I know would say no, not yet, not even close. But I was intrigued.”
Should We Start Taking the Welfare of A.I. Seriously?
As artificial intelligence systems become smarter, one A.I. company is trying to figure out what to do if they become conscious.
www.nytimes.com
April 24, 2025 at 6:24 PM
“is my calculator horny?“ our tech columnist asks. “i entered 5318008 into it and turned it upside down. what i saw surprised me”
Reposted by Ondrej Dusek
How do LLMs compare to human crowdworkers in annotating text spans? 🧑🤖
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
Large Language Models as Span Annotators
Website for the paper Large Language Models as Span Annotators
llm-span-annotators.github.io
April 15, 2025 at 11:10 AM
How do LLMs compare to human crowdworkers in annotating text spans? 🧑🤖
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
Reposted by Ondrej Dusek
Participate in the 👉 CRAC 2025 Shared Task on Multilingual Coreference Resolution❗ ufal.mff.cuni.cz/corefud/crac25
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
April 9, 2025 at 3:02 PM
Participate in the 👉 CRAC 2025 Shared Task on Multilingual Coreference Resolution❗ ufal.mff.cuni.cz/corefud/crac25
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
If you have not already done so, register first. 👆 Then start discovering how words refer to each other in 1️⃣7️⃣ languages. This year includes a new ✨LLM✨ track 😮.
Reposted by Ondrej Dusek
A 3-year full-time post-doc position in Prague! I'll be grateful for reposts. Feel free to get in touch if you have questions. linguistlist.org/issues/36/10...
LINGUIST List 36.1018 Jobs: Morphology, Pragmatics, Semantics, Syntax: Post-Doc in Empirical and Theoretical Linguistics, Faculty of Arts, Charles University
The LINGUIST List, International Linguistics Community Online.
linguistlist.org
March 24, 2025 at 4:10 PM
A 3-year full-time post-doc position in Prague! I'll be grateful for reposts. Feel free to get in touch if you have questions. linguistlist.org/issues/36/10...
Reposted by Ondrej Dusek
It’s kind of quaint to think the big worry a few years ago was that AI chatbots would destroy humanity. We’re quite capable of doing that without their help.
March 22, 2025 at 11:09 AM
It’s kind of quaint to think the big worry a few years ago was that AI chatbots would destroy humanity. We’re quite capable of doing that without their help.
Reposted by Ondrej Dusek
👨💻👩💻 Pod vedením @ufal-cuni.bsky.social #MFFUK @unikarlova.cuni.cz se začíná budovat rodina velkých jazykových modelů pro všechny evropské jazyky. V Karolinu dnes odstartoval mezinárodní projekt @openeurollm.bsky.social. 👏
www.ukforum.cz/rubriky/aktu...
www.ukforum.cz/rubriky/aktu...
Univerzita Karlova v čele evropského výzkumu AI
„Naším hlavním cílem je vyrobit jazykový model, který bude konkurencí stávajícím modelům, a navíc bude fungovat velmi dobře pro všechny evropské jazyky,“ uvedl profesor Jan Hajič z ÚFAL MFF UK, který ...
www.ukforum.cz
March 7, 2025 at 2:45 PM
👨💻👩💻 Pod vedením @ufal-cuni.bsky.social #MFFUK @unikarlova.cuni.cz se začíná budovat rodina velkých jazykových modelů pro všechny evropské jazyky. V Karolinu dnes odstartoval mezinárodní projekt @openeurollm.bsky.social. 👏
www.ukforum.cz/rubriky/aktu...
www.ukforum.cz/rubriky/aktu...