Naomi Baes
@naomibaes.bsky.social
PhD Candidate | NLP • Psychology • Computational Social Science
- Build theory-driven frameworks (SIBling & LSC-Eval) to model semantic change in societally relevant concepts
- Supervisors: Nick Haslam & Kat Vylomova
🌐 naomibaes.github.io
- Build theory-driven frameworks (SIBling & LSC-Eval) to model semantic change in societally relevant concepts
- Supervisors: Nick Haslam & Kat Vylomova
🌐 naomibaes.github.io
Pinned
Naomi Baes
@naomibaes.bsky.social
· Jul 27
Excited to present LSC-Eval @aclmeeting.bsky.social! 🎉
This general-purpose framework evaluates methods for assessing dimensions of lexical semantic change using LLM-generated synthetic data to test how well measures detect changes.
📍MON @ 6 pm, Hall 4/5
Paper: aclanthology.org/2025.finding...
This general-purpose framework evaluates methods for assessing dimensions of lexical semantic change using LLM-generated synthetic data to test how well measures detect changes.
📍MON @ 6 pm, Hall 4/5
Paper: aclanthology.org/2025.finding...
Reposted by Naomi Baes
Just finished @lucyfoulkes.bsky.social' "What Mental Illness Really Is... (and what it isn't)." I think this is an excellent introduction to the topic -- providing lots of nuance without getting too technical, a critical eye on evidence, and lots of empathy for those who are struggling.>
February 18, 2025 at 2:45 PM
Just finished @lucyfoulkes.bsky.social' "What Mental Illness Really Is... (and what it isn't)." I think this is an excellent introduction to the topic -- providing lots of nuance without getting too technical, a critical eye on evidence, and lots of empathy for those who are struggling.>
Reposted by Naomi Baes
The International Workshop on Computational Approaches to Language Change - LChange'26 - will be co-located with EACL2026 in Morocco, March 24-29, 2026.
Details: www.changeiskey.org/event/2026-e...
#NLProc #EACL2026
Details: www.changeiskey.org/event/2026-e...
#NLProc #EACL2026
6th International Workshop on Computational Approaches to Language Change 2026 (LChange'26) | Change Is Key!
LChange'26 is the sixth workshop for computational approaches to language change with the focus on digital text corpora. Come join us for this exciting adventure!
www.changeiskey.org
November 19, 2025 at 10:52 AM
The International Workshop on Computational Approaches to Language Change - LChange'26 - will be co-located with EACL2026 in Morocco, March 24-29, 2026.
Details: www.changeiskey.org/event/2026-e...
#NLProc #EACL2026
Details: www.changeiskey.org/event/2026-e...
#NLProc #EACL2026
Reposted by Naomi Baes
📢 Call for Papers: LChange’26 - 6th International Workshop on Computational Approaches to Language Change 2026.
Co-located with EACL 2026, Rabat, Morocco & online (March 24–29, 2026).
Submissions due Dec 19 2025 (Direct) / Jan 2 2026 (ARR).
🌐 www.changeiskey.org/event/2026-e...
Co-located with EACL 2026, Rabat, Morocco & online (March 24–29, 2026).
Submissions due Dec 19 2025 (Direct) / Jan 2 2026 (ARR).
🌐 www.changeiskey.org/event/2026-e...
6th International Workshop on Computational Approaches to Language Change 2026 (LChange'26) | Change Is Key!
LChange'26 is the sixth workshop for computational approaches to language change with the focus on digital text corpora. Come join us for this exciting adventure!
www.changeiskey.org
October 15, 2025 at 11:03 AM
📢 Call for Papers: LChange’26 - 6th International Workshop on Computational Approaches to Language Change 2026.
Co-located with EACL 2026, Rabat, Morocco & online (March 24–29, 2026).
Submissions due Dec 19 2025 (Direct) / Jan 2 2026 (ARR).
🌐 www.changeiskey.org/event/2026-e...
Co-located with EACL 2026, Rabat, Morocco & online (March 24–29, 2026).
Submissions due Dec 19 2025 (Direct) / Jan 2 2026 (ARR).
🌐 www.changeiskey.org/event/2026-e...
Reposted by Naomi Baes
Keynote spotlight #3: COLM's second day will open with some *real* intelligence 🧠🧠🧠 with Tom Griffiths from Princeton
September 18, 2025 at 4:17 PM
Keynote spotlight #3: COLM's second day will open with some *real* intelligence 🧠🧠🧠 with Tom Griffiths from Princeton
Reposted by Naomi Baes
I will be at #COLM2025 this week, and would love to connect with folks interested in applications (and critiques) of language modeling in social science research!
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
NLP 4 Democracy - COLM 2025
sites.google.com
October 6, 2025 at 7:31 PM
I will be at #COLM2025 this week, and would love to connect with folks interested in applications (and critiques) of language modeling in social science research!
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
Reposted by Naomi Baes
I elaborate on what I think should be taught. It boils down to (at least) four things:
1 causality: how to pose and identify effects
2 regression: as a tool for inference, not prediction
3 benchmarks: as measurements, not trophies
4 experiments: with rigor, power, and ethics
1 causality: how to pose and identify effects
2 regression: as a tool for inference, not prediction
3 benchmarks: as measurements, not trophies
4 experiments: with rigor, power, and ethics
October 5, 2025 at 4:07 PM
I elaborate on what I think should be taught. It boils down to (at least) four things:
1 causality: how to pose and identify effects
2 regression: as a tool for inference, not prediction
3 benchmarks: as measurements, not trophies
4 experiments: with rigor, power, and ethics
1 causality: how to pose and identify effects
2 regression: as a tool for inference, not prediction
3 benchmarks: as measurements, not trophies
4 experiments: with rigor, power, and ethics
Reposted by Naomi Baes
[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.
April 7, 2025 at 1:54 PM
[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.
Honored to give a talk at the National Research Council Canada on Dimensions of Semantic Change, thanks to Dr Saif Mohammad (NRC-VAD mastermind).
Shared 2 frameworks - SIBling (Sentiment, Intensity, Breadth) + LSC-Eval - applied to mental health concepts.
Slides: www.slideshare.net/slideshow/di...
Shared 2 frameworks - SIBling (Sentiment, Intensity, Breadth) + LSC-Eval - applied to mental health concepts.
Slides: www.slideshare.net/slideshow/di...
September 24, 2025 at 7:28 PM
Honored to give a talk at the National Research Council Canada on Dimensions of Semantic Change, thanks to Dr Saif Mohammad (NRC-VAD mastermind).
Shared 2 frameworks - SIBling (Sentiment, Intensity, Breadth) + LSC-Eval - applied to mental health concepts.
Slides: www.slideshare.net/slideshow/di...
Shared 2 frameworks - SIBling (Sentiment, Intensity, Breadth) + LSC-Eval - applied to mental health concepts.
Slides: www.slideshare.net/slideshow/di...
Reposted by Naomi Baes
Pleased to announce our #NLP SemEval Task 7: Everyday Knowledge Across Diverse Languages & Cultures.
We extend the BLEnD Benchmark to >30 language-culture pairs. [Our task is Junior-friendly, with live Q&A & tutorials.] 1/
We extend the BLEnD Benchmark to >30 language-culture pairs. [Our task is Junior-friendly, with live Q&A & tutorials.] 1/
September 22, 2025 at 11:14 AM
Pleased to announce our #NLP SemEval Task 7: Everyday Knowledge Across Diverse Languages & Cultures.
We extend the BLEnD Benchmark to >30 language-culture pairs. [Our task is Junior-friendly, with live Q&A & tutorials.] 1/
We extend the BLEnD Benchmark to >30 language-culture pairs. [Our task is Junior-friendly, with live Q&A & tutorials.] 1/
Reposted by Naomi Baes
*SEM 2025 invites presentations of accepted EMNLP Findings papers that fit the theme. Register your paper by September 24! Registration link: docs.google.com/forms/d/e/1F...
#NLP #NLProc
#NLP #NLProc
*SEM2025 Request to Present Accepted EMNLP Findings Paper
*SEM2025 may be able to accommodate presentation of relevant papers accepted for Findings of EMNLP 2025. Please refer to the *SEM2025 CFP to ensure your paper is relevant.
The deadline for applicati...
docs.google.com
September 18, 2025 at 6:06 AM
*SEM 2025 invites presentations of accepted EMNLP Findings papers that fit the theme. Register your paper by September 24! Registration link: docs.google.com/forms/d/e/1F...
#NLP #NLProc
#NLP #NLProc
Gave a talk @utrechtuniversity.bsky.social NLTP Lab — thanks for the kind invitation and stimulating discussion!
I presented:
🔹SIBling – models semantic change (Sentiment, Intensity, Breadth)
🔹LSC-Eval – synthetic benchmarks for evaluating change methods
Slides: www.slideshare.net/slideshow/di...
I presented:
🔹SIBling – models semantic change (Sentiment, Intensity, Breadth)
🔹LSC-Eval – synthetic benchmarks for evaluating change methods
Slides: www.slideshare.net/slideshow/di...
Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts
Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts Invited by: Dr. Pablo Mosteiro Romero: https://www.uu.nl/staff/PJMosteiroRomero Location: Natural Language and Text Processing Lab, University of Utrecht: https://nlp.sites.uu.nl/ Promotion: https://nlp.sites.uu.nl/2025/09/11/nltp-content-meetings-september-16-dimensions-of-semantic-change-applying-the-sibling-framework-to-mental-health-concepts-by-naomi-baes/ Title: Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts Abstract: Lexical semantic change takes many forms, yet existing approaches often examine them in isolation. I present SIBling, a three-dimensional framework for modelling semantic change through shifts in (1) Sentiment (the valence of a word’s contexts), (2) Intensity (emotional arousal or the use of intensifiers), and (3) Breadth (the diversity of contexts in which a word appears). Together, these dimensions provide an integrated and computationally efficient way of mapping how the meanings of concepts evolve over time. I illustrate the framework with case studies of mental health related concepts, showing how they have broadened, intensified, or shifted in sentiment across decades of text. These results illuminate cultural trends such as pathologization, stigma, and concept creep, demonstrating how the SIBling toolkit captures capture socially significant conceptual change. Main publications the presentation is based on: 1. Naomi Baes, Nick Haslam, and Ekaterina Vylomova. 2024. A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1390–1415, Bangkok, Thailand. Association for Computational Linguistics. 2. Naomi Baes, Raphael Merx, Nick Haslam, Ekaterina Vylomova, and Haim Dubossarsky. 2025. LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data. In Findings of the Association for Computational Linguistics: ACL 2025, pages 10905–10939, Vienna, Austria. Association for Computational Linguistics. - Download as a PDF or view online for free
www.slideshare.net
September 16, 2025 at 9:49 AM
Gave a talk @utrechtuniversity.bsky.social NLTP Lab — thanks for the kind invitation and stimulating discussion!
I presented:
🔹SIBling – models semantic change (Sentiment, Intensity, Breadth)
🔹LSC-Eval – synthetic benchmarks for evaluating change methods
Slides: www.slideshare.net/slideshow/di...
I presented:
🔹SIBling – models semantic change (Sentiment, Intensity, Breadth)
🔹LSC-Eval – synthetic benchmarks for evaluating change methods
Slides: www.slideshare.net/slideshow/di...
The recent killing of Charlie Kirk underscores the urgency of this timely essay by Professor Shalom Lappin. It charts how three illiberal movements — authoritarian New Right, postmodern anti-colonial Left, and Islamist extremism — have surged from the fringes.
Link: quillette.com/2025/08/21/t...
Link: quillette.com/2025/08/21/t...
The Neo-Romantic Revolt
The rise of a three-pronged politics of unreason.
quillette.com
September 13, 2025 at 9:02 AM
The recent killing of Charlie Kirk underscores the urgency of this timely essay by Professor Shalom Lappin. It charts how three illiberal movements — authoritarian New Right, postmodern anti-colonial Left, and Islamist extremism — have surged from the fringes.
Link: quillette.com/2025/08/21/t...
Link: quillette.com/2025/08/21/t...
Had an intellectually stimulating time at the Language models And RePresentations (LARP) 2025 conference, exploring ideas around neuro-symbolic AI and enjoying excellent keynotes from Moa Johansson, Dan Roth, and Vaishak Belle.
See proceedings here: gu-clasp.github.io/LARP/program...
See proceedings here: gu-clasp.github.io/LARP/program...
September 9, 2025 at 1:40 PM
Had an intellectually stimulating time at the Language models And RePresentations (LARP) 2025 conference, exploring ideas around neuro-symbolic AI and enjoying excellent keynotes from Moa Johansson, Dan Roth, and Vaishak Belle.
See proceedings here: gu-clasp.github.io/LARP/program...
See proceedings here: gu-clasp.github.io/LARP/program...
Excited to be speaking at Change is Key! (University of Gothenburg) on "Dimensions of Semantic Change: Validation and Application of the SIBling Framework"
I’ll show how SIBling (Sentiment, Intensity, Breadth) helps track semantic change in mental health terms.
Link: www.gu.se/en/event/cha...
I’ll show how SIBling (Sentiment, Intensity, Breadth) helps track semantic change in mental health terms.
Link: www.gu.se/en/event/cha...
Change is Key! – Using LLMs in the Humanities and Social Sciences
Come and learn about computational modeling of linguistic, cultural and social change. Welcome to a full-day conference at Humanisten, organized by the research project Change is Key! We will present ...
www.gu.se
September 5, 2025 at 4:55 AM
Excited to be speaking at Change is Key! (University of Gothenburg) on "Dimensions of Semantic Change: Validation and Application of the SIBling Framework"
I’ll show how SIBling (Sentiment, Intensity, Breadth) helps track semantic change in mental health terms.
Link: www.gu.se/en/event/cha...
I’ll show how SIBling (Sentiment, Intensity, Breadth) helps track semantic change in mental health terms.
Link: www.gu.se/en/event/cha...
Reposted by Naomi Baes
We wrote a little overview chapter on Evolutionary Linguistics with Jonas Nölle and @stefanhartmann.bsky.social for the upcoming Encyclopedia of Language and Linguistics (3rd ed), edited by Nesi&Milin. Preprint here: osf.io/preprints/ps... (with extra references! the handbook had a limit on those)
September 1, 2025 at 11:38 AM
We wrote a little overview chapter on Evolutionary Linguistics with Jonas Nölle and @stefanhartmann.bsky.social for the upcoming Encyclopedia of Language and Linguistics (3rd ed), edited by Nesi&Milin. Preprint here: osf.io/preprints/ps... (with extra references! the handbook had a limit on those)
Reposted by Naomi Baes
If you missed us at #cogsci2025, my lab presented 3 new studies showing how efficient (lossy) compression shapes individual learners, bilinguals, and action abstractions in language, further demonstrating the extraordinary applicability of this principle to human cognition! 🧵
1/n
1/n
August 9, 2025 at 1:46 PM
If you missed us at #cogsci2025, my lab presented 3 new studies showing how efficient (lossy) compression shapes individual learners, bilinguals, and action abstractions in language, further demonstrating the extraordinary applicability of this principle to human cognition! 🧵
1/n
1/n
Reposted by Naomi Baes
A nice discovery today: #ic2s2 keynotes are on Youtube! In particular, I think the papers listed by @lauraknelson.bsky.social in her keynote could form a great list for a CSS reading group.
www.youtube.com/watch?v=NXYg...
www.youtube.com/watch?v=NXYg...
Laura Nelson: Qualitative Methods for Computational Social Science — IC2S2 2025 Keynote
YouTube video by Institute for Analytical Sociology
www.youtube.com
August 12, 2025 at 12:58 AM
A nice discovery today: #ic2s2 keynotes are on Youtube! In particular, I think the papers listed by @lauraknelson.bsky.social in her keynote could form a great list for a CSS reading group.
www.youtube.com/watch?v=NXYg...
www.youtube.com/watch?v=NXYg...
Reposted by Naomi Baes
Enjoyed this interview with Ricardo on @thedissenteryt.bsky.social ! We discussed different types of causation, the topic of explanation in science, & my recent Cambridge Univ Press Elements book on "Explanation in biology" 📕
YouTube: youtu.be/sbY40h-1gKY
Book: www.cambridge.org/core/element...
YouTube: youtu.be/sbY40h-1gKY
Book: www.cambridge.org/core/element...
New episode (1061), with Dr. Lauren Ross (@laurennross.bsky.social). We talk about causation and explanation in #Science. #Philosophy
YouTube: youtu.be/sbY40h-1gKY
Podcast: bit.ly/4hLHjvL
YouTube: youtu.be/sbY40h-1gKY
Podcast: bit.ly/4hLHjvL
February 21, 2025 at 3:36 PM
Enjoyed this interview with Ricardo on @thedissenteryt.bsky.social ! We discussed different types of causation, the topic of explanation in science, & my recent Cambridge Univ Press Elements book on "Explanation in biology" 📕
YouTube: youtu.be/sbY40h-1gKY
Book: www.cambridge.org/core/element...
YouTube: youtu.be/sbY40h-1gKY
Book: www.cambridge.org/core/element...
Reposted by Naomi Baes
I am delighted to share our new #PNAS paper, with @grvkamath.bsky.social @msonderegger.bsky.social and @sivareddyg.bsky.social, on whether age matters for the adoption of new meanings. That is, as words change meaning, does the rate of adoption vary across generations? www.pnas.org/doi/epdf/10....
July 29, 2025 at 12:31 PM
I am delighted to share our new #PNAS paper, with @grvkamath.bsky.social @msonderegger.bsky.social and @sivareddyg.bsky.social, on whether age matters for the adoption of new meanings. That is, as words change meaning, does the rate of adoption vary across generations? www.pnas.org/doi/epdf/10....
Reposted by Naomi Baes
This week, we had the pleasure of hosting @christinenlp.bsky.social , who presented her work on 'Modelling the Language of Extremist Groups.' Thank you for visiting us!
August 8, 2025 at 11:58 AM
This week, we had the pleasure of hosting @christinenlp.bsky.social , who presented her work on 'Modelling the Language of Extremist Groups.' Thank you for visiting us!
Reposted by Naomi Baes
Will the Australian government really lock under-16s out of TikTok? A/Prof Scott Griffiths returns to PsychTalks to unpack the proposed social media ban. He breaks down policy motives, enforcement hurdles, and how parents can protect kids’ mental health online.
🎧Find it here go.unimelb.edu.au/7axe
🎧Find it here go.unimelb.edu.au/7axe
August 3, 2025 at 10:59 PM
Will the Australian government really lock under-16s out of TikTok? A/Prof Scott Griffiths returns to PsychTalks to unpack the proposed social media ban. He breaks down policy motives, enforcement hurdles, and how parents can protect kids’ mental health online.
🎧Find it here go.unimelb.edu.au/7axe
🎧Find it here go.unimelb.edu.au/7axe
Reposted by Naomi Baes
*SEM 2025 call for ARR commit papers! *SEM 2025 will be co-located with EMNLP and accepts commits of ARR papers with complete sets of ARR reviews. Commit your paper here by Aug 22: openreview.net/group?id=acl...
#NLP #NLProc
#NLP #NLProc
StarSEM 2025 ARR Commitment
Welcome to the OpenReview homepage for StarSEM 2025 ARR Commitment
openreview.net
July 31, 2025 at 7:38 AM
*SEM 2025 call for ARR commit papers! *SEM 2025 will be co-located with EMNLP and accepts commits of ARR papers with complete sets of ARR reviews. Commit your paper here by Aug 22: openreview.net/group?id=acl...
#NLP #NLProc
#NLP #NLProc
Reposted by Naomi Baes
Our paper on #ChildObjectification on TikTok is finally out! Check out my poster presentation tomorrow at the #Workshop on #Online #Abuse and #Harms @ #ACL.
⬇️ Read more about our findings in the post below!
aclanthology.org/2025.woah-1....
⬇️ Read more about our findings in the post below!
aclanthology.org/2025.woah-1....
Join my talk on #ChildObjectification on TikTok at #IC2S2 today at 2:30 PM (📍 Social Good & Ethics).
I built classification models to detect objectifying language and found: 10% of comments refer to appearance, 3% are objectifying. Models struggle with this task, with #RoBERTa outperforming GPT-4.
I built classification models to detect objectifying language and found: 10% of comments refer to appearance, 3% are objectifying. Models struggle with this task, with #RoBERTa outperforming GPT-4.
July 31, 2025 at 12:14 PM
Our paper on #ChildObjectification on TikTok is finally out! Check out my poster presentation tomorrow at the #Workshop on #Online #Abuse and #Harms @ #ACL.
⬇️ Read more about our findings in the post below!
aclanthology.org/2025.woah-1....
⬇️ Read more about our findings in the post below!
aclanthology.org/2025.woah-1....
Reposted by Naomi Baes
Our ✨BRIGHTER✨ paper won the a best resource paper award at @aclmeeting.bsky.social #ACL2025!
Big thanks to all the team members!
Big thanks to all the team members!
July 30, 2025 at 6:35 PM
Our ✨BRIGHTER✨ paper won the a best resource paper award at @aclmeeting.bsky.social #ACL2025!
Big thanks to all the team members!
Big thanks to all the team members!