🎙️ In #WiAIR, we talk with Sophia Simeng Han, PhD student at Yale University, about her paper:
“Creativity or Brute Force? Using Brainteasers as a Window into LLMs”.
🔗 Paper: arxiv.org/pdf/2505.10844 (2/8)
#NAACL2025 #AIResearch
🎙 In #WiAIR, we talk with Sophia Simeng Han, PhD student at Yale University, about her paper:
“Creativity or Brute Force? Using Brainteasers as a Window into LLMs”.
🔗 Paper: arxiv.org/pdf/2505.10844 (2/8)
#NAACL2025 #AIResearch
Excited to attend #ACL2025NLP in Vienna next week!
I’ll be presenting our #NAACL2025 paper, PICLe, at the first workshop on Large Language Models and Structure Modeling (XLLM) on Friday. Come by our poster if you’re into NER and ICL with pseudo-annotation.
arxiv.org/abs/2412.11923
Illustration of a young woman wearing an academic cap and lab coat, closely examining a document with a magnifying glass. A robotic parrot sits on her shoulder, suggesting a blend of science, research, and technology. The style is monochrome with clean, cartoon-like lines.
🚀 𝗟𝗮𝘁𝗲𝘀𝘁 𝗣𝗲𝗲𝗿 𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗳𝗿𝗼𝗺 𝗔𝗥𝗥 𝟮𝟬𝟮𝟱!
tudatalib.ulb.tu-darmstadt.de/handle/tudat...
This 𝗻𝗲𝘄 𝗱𝗮𝘁𝗮𝘀𝗲𝘁 expands on previous releases, now including review data from #COLING2025 and #NAACL2025.
(1/🧵)
#NAACL2025 ended more than a week ago & @ufal-cuni.bsky.social folks were there:
Main conf: @kathaem.bsky.social presented joint work w/ @tomlim.bsky.social, @jlibovicky.bsky.social and Alex Fraser: Beyond Literal Token Overlap: Token Alignability for Multilinguality aclanthology.org/2025.naacl-s...
Happy that our work on multicultural hate meme detection was honored with an Outstanding Paper Award at #NAACL2025! 🏆 This effort was led by
@minhducbui.bsky.social during the time he spent as a visiting researcher with us — congratulations, Duc!🚀 #LLMs #NLProc
#NAACL2025 recap'! 🇺🇸
Last week, Salim Aissi was in Albuquerque to present his poster "Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting"!
Link to the paper ⬇️
aclanthology.org/2025.finding...
📢The paper “MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation” by U. Sentsova, D. Ciminari, J. Van Genabith & C. España-Bonet received the Best Paper Award at the 21st Workshop on Multiword Expressions at #NAACL2025.
Congratulations!
👁🗨 aclanthology.org/2025.naacl-l...
💡This work presents a detailed analysis of strategies for developing a model capable of following instructions in a low-resource language by focusing on three key stages
🔸pre-training
🔸instruction tuning
🔸alignment with human preferences
#NAACL2025
#OraiNLP
Had so many fruitful discussions and made many friends this #NAACL2025 🌵🏜️Thanks for everyone who came to my poster or listened to me talking about my audacious thoughts! 😜
(I should have printed more stickers as they were more popular than I anticipated😅)
We have a virtual award session at 14:30 (MT).
You can get to the Gather through Underline, either using the coffee cup icon on the left, or by navigating to one of the awards sessions and clicking the gather link for a talk. #NAACL2025
🌐 We are in #NAACL2025
🗣️ Ander Corral, researcher at #OraiNLP, will present some strategies for developing #LLMs capable of understanding #Basque language instructions
📰 Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque
#LlamaEUS
#NAACL2025 proceedings: great collaboration with @myrthereuver.bsky.social @indiiigo.bsky.social, @matteo-mls.bsky.social on the interactions between LLMs and SocSci experts for sexism detection
#NAACL2025 virtual conference today! Iman Jundi will present our work on the generation of positive moderation Curious what it is? Drop by or read our paper! aclanthology.org/2025.naacl-l... @ims-stuttgart.bsky.social @gesis.org @hhu.de @unihannover.bsky.social
Cerramos una semana fabulosa en #NAACL2025 con el segundo día de workshops. Ahora en AmericasNLP keynote de @alexispalmer.bsky.social y panel de discusión sobre desafíos y oportunidades de PLN para lenguas indígenas
Justin Vasselli online now presenting our winning entry for the AmericasNLP task on Educational Materials from Learning Resources for Indigenous Languages of the Americas at #NAACL2025!
Last day of #NAACL2025! We have two posters today at 2:30pm at Hall 3! Come say 👋! 🧵:
🎉 Exciting first session with paper presentations and a keynote talk at the AmericasNLP 2025 workshop!
We have much more lined up for the rest of the day -- join us in-person or on Zoom! ✨
#NLProc #NAACL2025
Slide by Alie Lassche on tasks and hypotheses of their work on canonization in Danish literature
@alielassche.bsky.social presents joined work on #canonization, proposing "non-canonical canonicals", referring to earlier findings in Feldkamp et al. (2024). "A canonical textual profile is not enough to become canonical". #NAACL2025 #SIGHUM
Janis Pagel on the right side of the picture introduces Computational Literary Studies to the workshop audience at SIGHUM NAACL2025. Slides with explanation of CLS
@janispagel introduces #CLS to the audience at #NAACL2025 #SIGHUM. The paper "Evaluating LLM-Prompting for Sequence Labeling Tasks in Computational Literary Studies" evaluates #SentimentAnalysis and #EventDetection tasks with #LLMs. https://aclanthology.org/2025.latechclfl-1.0/
Screenshot of SIGHUM website with head of the workshop program
Final day of #NAACL2025 + workshops, it’s time for #SIGHUM LaTeCH CLfL 2025 #DigitalHumanities #LanguageTechnology #Socio-EconomicSciences #Humanities
Slide by Alie Lassche on tasks and hypotheses of their work on canonization in danish literature
@alielassche.bsky.social presents joined work on #canonization, proposing "non-canonical canonicals", referring to earlier findings in Feldkamp et al. (2024). "A canonical textual profile is not enough to become canonical". #NAACL2025 #SIGHUM
✨Join us for the AmericasNLP Workshop today ✨
We have an exciting lineup of keynote talks, paper presentations, and posters!
In-person at NAACL 2025 or virtually on Zoom.
#NLProc #NAACL2025
Happening now at #NAACL2025 in room Pecos.
Kicking off with amazing talks and a panel by Monojit Choudhury, Isabelle Augenstein, and Katia Shutova
Happening now at @americasnlp.bsky.social 2025. Telegram in Aymara and how to translate tech terminology. #NAACL2025
Janis Pagel introducing Computational Literary Studies to the workshop audience at SIGHUM NAACL2025. Slide with explanation of CLS.
Janis Pagel from @idhcologne.bsky.social introduces #CLS to the audience at #NAACL2025 #SIGHUM. Their paper "Evaluating LLM-Prompting for Sequence Labeling Tasks in Computational Literary Studies" evaluates #SentimentAnalysis and #EventDetection tasks with #LLMs. aclanthology.org/2025.latechc...
Screenshot of SIGHUM website with head of the workshop program
Final day of #NAACL2025 + workshops, it’s time for #SIGHUM LaTeCH CLfL 2025 #DigitalHumanities #LanguageTechnology #Socio-EconomicSciences #Humanities
Excited to present tomorrow at the @c3nlp.bsky.social workshop at #NAACL2025 our position paper:
"Hire Your Anthropologist!" 🎓
Led by the amazing Mai Alkhamissi & @lrz-persona.bsky.social, under the supervision of @monadiab77.bsky.social. Don’t miss it! 😄
arXiv link coming soon!
Title slide: Processing Trans Languaging - Vagrant Gautam (they/xe), Saarland University, with a very brightly patterned background featuring colourful people and math symbols.
Come to my keynote tomorrow at the first official @queerinai.com workshop at #NAACL2025 to hear about how trans languaging is complex and cool, and how this makes it extra difficult to process computationally. I will have SO many juicy examples!
Excited to present our work at #NAACL2025 in Albuquerque! We tackle a core question: What fundamental information is needed to effectively simulate human identity in AI agents?
