Show threadMLIA ISIRMay 7, 2025

#NAACL2025 recap'! ๐Ÿ‡บ๐Ÿ‡ธ
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 โฌ‡๏ธ
https://aclanthology.org/2025.findings-naacl.390/

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting

Mohamed Salim Aissi, Clรฉment Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.

ACL Anthology
Svenja GuhrMay 4, 2025
@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
Svenja GuhrMay 4, 2025
@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/
Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)

Anna Kazantseva, Stan Szpakowicz, Stefania Degaetano-Ortlieb, Yuri Bizzoni, Janis Pagel. Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025). 2025.

ACL Anthology
Svenja GuhrMay 4, 2025
Final day of #NAACL2025 + workshops, itโ€™s time for #SIGHUM LaTeCH CLfL 2025 #DigitalHumanities #LanguageTechnology #Socio-EconomicSciences #Humanities
Svenja GuhrMay 4, 2025
Final day of #NAACL2025 + workshops, itโ€™s time for #SIGHUM LaTeCH CLfL 2025 #DigitalHumanities #LanguageTechnology #Socio-EconomicSciences #Humanities
Bluesky

Bluesky Social
ArturoApr 29, 2025
#NAACL2025 is starting!
Show threadUKP LabApr 29, 2025

And consider following the authors Ahmed Elshabrawy, Yongxin Huang, Iryna Gurevych and Alham Fikri Aji if you are interested in more information or an exchange of ideas. (6/6)

See you in Albuquerque ๐ŸŒต! #NAACL2025

UKP LabApr 29, 2025

๐Ÿš€ ๐—ฆ๐—ข๐—ง๐—” ๐Ÿฌ-๐˜€๐—ต๐—ผ๐˜ ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€ ๐—ด๐—ฟ๐—ผ๐˜„๐—ถ๐—ป๐—ด? ๐˜ฟ๐™ค๐™ฃ'๐™ฉ ๐™—๐™ง๐™š๐™–๐™  ๐™ฉ๐™๐™š ๐™˜๐™ค๐™ข๐™ฅ๐™ช๐™ฉ๐™š-๐™—๐™–๐™ฃ๐™ ! โšก๐Ÿ’ก

Discover Statement-Tuning in our #NAACL2025 paper: we transform NLU tasks into natural language statements, letting small models like RoBERTa shine โœจ in zero & few-shot settings at a fraction of the cost. ๐Ÿ”ฅ
(1/๐Ÿงต)

#NLProc

UKP LabApr 29, 2025

๐—ก๐—ฒ๐˜„ ๐˜„๐—ผ๐—ฟ๐—ธ ๐—ผ๐—ป ๐˜๐—ฒ๐—บ๐—ฝ๐—น๐—ฎ๐˜๐—ถ๐—ฐ ๐—บ๐—ฒ๐—บ๐—ฒ๐˜€!
We built a knowledge base of 5,200+ meme templates & 54,000+ examples to study their encoded meaning.

Our #NAACL2025 paper shows how we can resplit datasets with templates for better generalization!

๐Ÿ“„: arxiv.org/abs/2311.06649 (1/๐Ÿงต)

#NLProc

Show threadUKP LabApr 28, 2025

And consider following the authors Falko Helm, Nico Daheim & Iryna Gurevych if you are interested in more information or an exchange of ideas. (5/5)

See you this week in Albuquerque ๐ŸŒต! #NAACL2025