Leonie Weissweiler
@weissweiler.bsky.social
Postdoc at Uppsala University Computational Linguistics with Joakim Nivre
PhD from LMU Munich, prev. UT Austin, Princeton, @ltiatcmu.bsky.social, Cambridge
computational linguistics, construction grammar, morphosyntax
leonieweissweiler.github.io
PhD from LMU Munich, prev. UT Austin, Princeton, @ltiatcmu.bsky.social, Cambridge
computational linguistics, construction grammar, morphosyntax
leonieweissweiler.github.io
Pinned
✨New paper✨
Linguistic evaluations of LLMs often implicitly assume that language is generated by symbolic rules.
In a new position paper, @adelegoldberg.bsky.social, @kmahowald.bsky.social and I argue that languages are not Lego sets, and evaluations should reflect this!
arxiv.org/pdf/2502.13195
Linguistic evaluations of LLMs often implicitly assume that language is generated by symbolic rules.
In a new position paper, @adelegoldberg.bsky.social, @kmahowald.bsky.social and I argue that languages are not Lego sets, and evaluations should reflect this!
arxiv.org/pdf/2502.13195
📢Out now in NEJLT!📢
In each of these sentences, a verb that doesn't usually encode motion is being used to convey that an object is moving to a destination.
Given that these usages are rare, complex, and creative, we ask:
Do LLMs understand what's going on in them?
🧵1/7
In each of these sentences, a verb that doesn't usually encode motion is being used to convey that an object is moving to a destination.
Given that these usages are rare, complex, and creative, we ask:
Do LLMs understand what's going on in them?
🧵1/7
November 19, 2025 at 1:57 PM
📢Out now in NEJLT!📢
In each of these sentences, a verb that doesn't usually encode motion is being used to convey that an object is moving to a destination.
Given that these usages are rare, complex, and creative, we ask:
Do LLMs understand what's going on in them?
🧵1/7
In each of these sentences, a verb that doesn't usually encode motion is being used to convey that an object is moving to a destination.
Given that these usages are rare, complex, and creative, we ask:
Do LLMs understand what's going on in them?
🧵1/7
Reposted by Leonie Weissweiler
Oh cool! Excited this LM + construction paper was SAC-Highlighted! Check it out to see how LM-derived measures of statistical affinity separate out constructions with similar words like "I was so happy I saw you" vs "It was so big it fell over".
Josh Rozner's paper (w/ @rifter.bsky.social + @kmahowald.bsky.social) was an SAC Highlight at #EMNLP25! aclanthology.org/2025.emnlp-m...
November 10, 2025 at 4:27 PM
Oh cool! Excited this LM + construction paper was SAC-Highlighted! Check it out to see how LM-derived measures of statistical affinity separate out constructions with similar words like "I was so happy I saw you" vs "It was so big it fell over".
I can confirm that I was indeed the 2nd author!
Not sure what went wrong there but the 2nd author was @weissweiler.bsky.social, so sorry Leonie!
Josh Rozner's paper (w/ @rifter.bsky.social + @kmahowald.bsky.social) was an SAC Highlight at #EMNLP25! aclanthology.org/2025.emnlp-m...
November 10, 2025 at 8:12 PM
I can confirm that I was indeed the 2nd author!
Reposted by Leonie Weissweiler
There's many directions where this could go, multilingual, low-resource language, interpretability, depending on your profile, and the internship may lead to a PhD, provided we get funding!
November 6, 2025 at 9:07 AM
There's many directions where this could go, multilingual, low-resource language, interpretability, depending on your profile, and the internship may lead to a PhD, provided we get funding!
Reposted by Leonie Weissweiler
As we found in aclanthology.org/2025.coling-... that BPE-based LLMs (i.e. pretty much all LLMs) did not handle prefixations well
Unlike “Likely”, “Unlike” is Unlikely: BPE-based Segmentation hurts Morphological Derivations in LLMs
Paul Lerner, François Yvon. Proceedings of the 31st International Conference on Computational Linguistics. 2025.
aclanthology.org
November 6, 2025 at 9:06 AM
As we found in aclanthology.org/2025.coling-... that BPE-based LLMs (i.e. pretty much all LLMs) did not handle prefixations well
Reposted by Leonie Weissweiler
Basically the idea is to extend www.pnas.org/doi/10.1073/... to see how well LLMs model competition between affixes, not only suffixes (e.g. -ity vs. -ness) but also prefixes (e.g. un- vs. non-)
Derivational morphology reveals analogical generalization in large language models | PNAS
What mechanisms underlie linguistic generalization in large language models (LLMs)?
This question has attracted considerable attention, with most s...
www.pnas.org
November 6, 2025 at 9:04 AM
Basically the idea is to extend www.pnas.org/doi/10.1073/... to see how well LLMs model competition between affixes, not only suffixes (e.g. -ity vs. -ness) but also prefixes (e.g. un- vs. non-)
Reposted by Leonie Weissweiler
Come work with @yvofr.bsky.social @weissweiler.bsky.social and me at @mlia-isir.bsky.social for a M2 internship on Assessing the Morphological Competence of LLMs! For 5-6 months from February or March 2026. Paid 600€/month
November 6, 2025 at 9:02 AM
Come work with @yvofr.bsky.social @weissweiler.bsky.social and me at @mlia-isir.bsky.social for a M2 internship on Assessing the Morphological Competence of LLMs! For 5-6 months from February or March 2026. Paid 600€/month
Reposted by Leonie Weissweiler
I'm in Suzhou to present our work on MultiBLiMP, Friday @ 11:45 in the Multilinguality session (A301)!
Come check it out if your interested in multilingual linguistic evaluation of LLMs (there will be parse trees on the slides! There's still use for syntactic structure!)
arxiv.org/abs/2504.02768
Come check it out if your interested in multilingual linguistic evaluation of LLMs (there will be parse trees on the slides! There's still use for syntactic structure!)
arxiv.org/abs/2504.02768
November 6, 2025 at 7:08 AM
I'm in Suzhou to present our work on MultiBLiMP, Friday @ 11:45 in the Multilinguality session (A301)!
Come check it out if your interested in multilingual linguistic evaluation of LLMs (there will be parse trees on the slides! There's still use for syntactic structure!)
arxiv.org/abs/2504.02768
Come check it out if your interested in multilingual linguistic evaluation of LLMs (there will be parse trees on the slides! There's still use for syntactic structure!)
arxiv.org/abs/2504.02768
📢Come join us in Uppsala to work on multilingual NLP as an independent postdoc with the most wonderful colleagues!
The deadline is Nov 26th, the expected start date is Feb 1st.
Feel free to shoot me an email if you want to hear more about this department and I will continue gushing about it.
The deadline is Nov 26th, the expected start date is Feb 1st.
Feel free to shoot me an email if you want to hear more about this department and I will continue gushing about it.
📢 Open Positions at the Uppsala NLP Group! 📢
Postdoc opportunity — also open to recent or soon-to-be PhD graduates (within 1–2 months).
uu.varbi.com/en/what:job/...
Postdoc opportunity — also open to recent or soon-to-be PhD graduates (within 1–2 months).
uu.varbi.com/en/what:job/...
November 4, 2025 at 3:23 PM
📢Come join us in Uppsala to work on multilingual NLP as an independent postdoc with the most wonderful colleagues!
The deadline is Nov 26th, the expected start date is Feb 1st.
Feel free to shoot me an email if you want to hear more about this department and I will continue gushing about it.
The deadline is Nov 26th, the expected start date is Feb 1st.
Feel free to shoot me an email if you want to hear more about this department and I will continue gushing about it.
Reposted by Leonie Weissweiler
Session 5: "BabyLM’s First Constructions." In a companion paper to the first one, we show that much of this constructional knowledge is even present in "babyLMs" with more developmentally plausible amounts of training: arxiv.org/abs/2506.02147. w/ @weissweiler.bsky.social
BabyLM's First Constructions: Causal probing provides a signal of learning
Construction grammar posits that language learners acquire constructions (form-meaning pairings) from the statistics of their environment. Recent work supports this hypothesis by showing sensitivity…
arxiv.org
November 2, 2025 at 9:57 PM
Session 5: "BabyLM’s First Constructions." In a companion paper to the first one, we show that much of this constructional knowledge is even present in "babyLMs" with more developmentally plausible amounts of training: arxiv.org/abs/2506.02147. w/ @weissweiler.bsky.social
Reposted by Leonie Weissweiler
Session 4: "Constructions are Revealed in Word Distributions." We show that rich knowledge of syntactic constructions in masked language models (MLMs) is revealed by patterns of contextual constraint. arxiv.org/abs/2503.06048. w/ @weissweiler.bsky.social + @kmahowald.bsky.social
Constructions are Revealed in Word Distributions
Construction grammar posits that constructions, or form-meaning pairings, are acquired through experience with language (the distributional learning hypothesis). But how much information about…
arxiv.org
November 2, 2025 at 9:57 PM
Session 4: "Constructions are Revealed in Word Distributions." We show that rich knowledge of syntactic constructions in masked language models (MLMs) is revealed by patterns of contextual constraint. arxiv.org/abs/2503.06048. w/ @weissweiler.bsky.social + @kmahowald.bsky.social
Reposted by Leonie Weissweiler
Reposted by Leonie Weissweiler
Happening now! Poster 42!
October 8, 2025 at 3:12 PM
Happening now! Poster 42!
Reposted by Leonie Weissweiler
Traveling to my first @colmweb.org🍁
Not presenting anything but here are two posters you should visit:
1. @qyao.bsky.social on Controlled rearing for direct and indirect evidence for datives (w/ me, @weissweiler.bsky.social and @kmahowald.bsky.social), W morning
Paper: arxiv.org/abs/2503.20850
Not presenting anything but here are two posters you should visit:
1. @qyao.bsky.social on Controlled rearing for direct and indirect evidence for datives (w/ me, @weissweiler.bsky.social and @kmahowald.bsky.social), W morning
Paper: arxiv.org/abs/2503.20850
Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models
Language models (LMs) tend to show human-like preferences on a number of syntactic phenomena, but the extent to which these are attributable to direct exposure to the phenomena or more general propert...
arxiv.org
October 6, 2025 at 3:22 PM
Traveling to my first @colmweb.org🍁
Not presenting anything but here are two posters you should visit:
1. @qyao.bsky.social on Controlled rearing for direct and indirect evidence for datives (w/ me, @weissweiler.bsky.social and @kmahowald.bsky.social), W morning
Paper: arxiv.org/abs/2503.20850
Not presenting anything but here are two posters you should visit:
1. @qyao.bsky.social on Controlled rearing for direct and indirect evidence for datives (w/ me, @weissweiler.bsky.social and @kmahowald.bsky.social), W morning
Paper: arxiv.org/abs/2503.20850
📢Life update📢
🥳I'm excited to share that I've started as a postdoc at Uppsala University NLP @uppsalanlp.bsky.social, working with Joakim Nivre on topics related to constructions and multilinguality!
🙏Many thanks to the Walter Benjamin Programme of the DFG for making this possible.
🥳I'm excited to share that I've started as a postdoc at Uppsala University NLP @uppsalanlp.bsky.social, working with Joakim Nivre on topics related to constructions and multilinguality!
🙏Many thanks to the Walter Benjamin Programme of the DFG for making this possible.
September 15, 2025 at 3:10 PM
📢Life update📢
🥳I'm excited to share that I've started as a postdoc at Uppsala University NLP @uppsalanlp.bsky.social, working with Joakim Nivre on topics related to constructions and multilinguality!
🙏Many thanks to the Walter Benjamin Programme of the DFG for making this possible.
🥳I'm excited to share that I've started as a postdoc at Uppsala University NLP @uppsalanlp.bsky.social, working with Joakim Nivre on topics related to constructions and multilinguality!
🙏Many thanks to the Walter Benjamin Programme of the DFG for making this possible.
Reposted by Leonie Weissweiler
Happening now at the SIGTYP poster session! Come talk to Leonie and me about MultiBLiMP!
August 1, 2025 at 10:17 AM
Happening now at the SIGTYP poster session! Come talk to Leonie and me about MultiBLiMP!
Hi #NLP community, I'm urgently looking for an emergency reviewer for the ARR Linguistic Theories track. The paper investigates and measures orthography across many languages. Please shoot me a quick email if you can review!
June 21, 2025 at 10:34 AM
Hi #NLP community, I'm urgently looking for an emergency reviewer for the ARR Linguistic Theories track. The paper investigates and measures orthography across many languages. Please shoot me a quick email if you can review!
I'm looking for a reviewer for a paper on measuring syntactic productivity (lots of maths!) due a week from now. Please shoot me an email if you could review!
June 11, 2025 at 8:36 PM
I'm looking for a reviewer for a paper on measuring syntactic productivity (lots of maths!) due a week from now. Please shoot me an email if you could review!
Reposted by Leonie Weissweiler
Do LLMs learn language via rules or analogies?
This could be a surprise to many – models rely heavily on stored examples and draw analogies when dealing with unfamiliar words, much as humans do. Check out this new study led by @valentinhofmann.bsky.social to learn how they made the discovery 💡
This could be a surprise to many – models rely heavily on stored examples and draw analogies when dealing with unfamiliar words, much as humans do. Check out this new study led by @valentinhofmann.bsky.social to learn how they made the discovery 💡
Thrilled to share that this is out in @pnas.org today! 🎉
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
📢 New paper 📢
What generalization mechanisms shape the language skills of LLMs?
Prior work has claimed that LLMs learn language via rules.
We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes.
🧵
What generalization mechanisms shape the language skills of LLMs?
Prior work has claimed that LLMs learn language via rules.
We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes.
🧵
May 9, 2025 at 10:51 PM
Do LLMs learn language via rules or analogies?
This could be a surprise to many – models rely heavily on stored examples and draw analogies when dealing with unfamiliar words, much as humans do. Check out this new study led by @valentinhofmann.bsky.social to learn how they made the discovery 💡
This could be a surprise to many – models rely heavily on stored examples and draw analogies when dealing with unfamiliar words, much as humans do. Check out this new study led by @valentinhofmann.bsky.social to learn how they made the discovery 💡
Reposted by Leonie Weissweiler
Thrilled to share that this is out in @pnas.org today! 🎉
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
📢 New paper 📢
What generalization mechanisms shape the language skills of LLMs?
Prior work has claimed that LLMs learn language via rules.
We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes.
🧵
What generalization mechanisms shape the language skills of LLMs?
Prior work has claimed that LLMs learn language via rules.
We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes.
🧵
May 9, 2025 at 6:29 PM
Thrilled to share that this is out in @pnas.org today! 🎉
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
We show that linguistic generalization in language models can be due to underlying analogical mechanisms.
Shoutout to my amazing co-authors @weissweiler.bsky.social, @davidrmortensen.bsky.social, Hinrich Schütze, and Janet Pierrehumbert!
Reposted by Leonie Weissweiler
Can self-supervised models 🤖 understand allophony 🗣? Excited to share my new #NAACL2025 paper: Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment arxiv.org/abs/2502.07029 (1/n)
April 29, 2025 at 5:00 PM
Can self-supervised models 🤖 understand allophony 🗣? Excited to share my new #NAACL2025 paper: Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment arxiv.org/abs/2502.07029 (1/n)
Reposted by Leonie Weissweiler
On my way to #NAACL2025 where I'll give a keynote at the noisy text workshop (WNUT), presenting some of the challenges & methods for dialect NLP + also discussing dialect speakers' perspectives!
🗨️ Beyond “noisy” text: How (and why) to process dialect data
🗓️ Saturday, May 3, 9:30–10:30
🗨️ Beyond “noisy” text: How (and why) to process dialect data
🗓️ Saturday, May 3, 9:30–10:30
April 29, 2025 at 9:17 AM
On my way to #NAACL2025 where I'll give a keynote at the noisy text workshop (WNUT), presenting some of the challenges & methods for dialect NLP + also discussing dialect speakers' perspectives!
🗨️ Beyond “noisy” text: How (and why) to process dialect data
🗓️ Saturday, May 3, 9:30–10:30
🗨️ Beyond “noisy” text: How (and why) to process dialect data
🗓️ Saturday, May 3, 9:30–10:30
🌍📣🥳
I could not be more excited for this to be out!
With a fully automated pipeline based on Universal Dependencies, 43 non-Indoeuropean languages, and the best LLMs only scoring 90.2%, I hope this will be a challenging and interesting benchmark for multilingual NLP.
Go test your language models!
I could not be more excited for this to be out!
With a fully automated pipeline based on Universal Dependencies, 43 non-Indoeuropean languages, and the best LLMs only scoring 90.2%, I hope this will be a challenging and interesting benchmark for multilingual NLP.
Go test your language models!
✨New paper ✨
Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages!
We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages.
🧵⬇️
Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages!
We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages.
🧵⬇️
April 7, 2025 at 3:03 PM
🌍📣🥳
I could not be more excited for this to be out!
With a fully automated pipeline based on Universal Dependencies, 43 non-Indoeuropean languages, and the best LLMs only scoring 90.2%, I hope this will be a challenging and interesting benchmark for multilingual NLP.
Go test your language models!
I could not be more excited for this to be out!
With a fully automated pipeline based on Universal Dependencies, 43 non-Indoeuropean languages, and the best LLMs only scoring 90.2%, I hope this will be a challenging and interesting benchmark for multilingual NLP.
Go test your language models!
We can use small LMs to test hypotheses about the language network and how everything is connected!
Here, we find that dative alternation preferences are learned from dative-specific input statistics *and* from more general short-first preferences.
Great work by @qyao.bsky.social, go follow him!
Here, we find that dative alternation preferences are learned from dative-specific input statistics *and* from more general short-first preferences.
Great work by @qyao.bsky.social, go follow him!
LMs learn argument-based preferences for dative constructions (preferring recipient first when it’s shorter), consistent with humans. Is this from memorizing preferences in training? New paper w/ @kanishka.bsky.social , @weissweiler.bsky.social , @kmahowald.bsky.social
arxiv.org/abs/2503.20850
arxiv.org/abs/2503.20850
March 31, 2025 at 3:04 PM
We can use small LMs to test hypotheses about the language network and how everything is connected!
Here, we find that dative alternation preferences are learned from dative-specific input statistics *and* from more general short-first preferences.
Great work by @qyao.bsky.social, go follow him!
Here, we find that dative alternation preferences are learned from dative-specific input statistics *and* from more general short-first preferences.
Great work by @qyao.bsky.social, go follow him!
Reposted by Leonie Weissweiler
Models have preferences like giving inanimate 📦 stuff to animate 👳
Is it that they just saw a lot of such examples in pretraining or is it generalization and deeper understanding?
alphaxiv.org/pdf/2503.20850
Is it that they just saw a lot of such examples in pretraining or is it generalization and deeper understanding?
alphaxiv.org/pdf/2503.20850
March 31, 2025 at 2:11 PM
Models have preferences like giving inanimate 📦 stuff to animate 👳
Is it that they just saw a lot of such examples in pretraining or is it generalization and deeper understanding?
alphaxiv.org/pdf/2503.20850
Is it that they just saw a lot of such examples in pretraining or is it generalization and deeper understanding?
alphaxiv.org/pdf/2503.20850