Domain experts use standards (documented rules) to create text content that aligns with their varying levels of required quality and interoperability. If you're attending #EMNLP2024 and this interests you, or if you're working on a similar project, please DM/reach out! 🙏

Catch this paper at #EMNLP2024 during the short poster session from 16:00-16:30 pm today and at the TSAR Workshop (TSAR 2024) this Friday. Paper: aclanthology.org/2024.findings-… Data: github.com/imperialite/sp…

ICML 2025 will require lay summaries (also called "plain language summaries") to increase accessibility and wider communication to non-experts and the public. This is a great initiative! The importance of plain languages was also discussed by Iria da Cunha TSAR 2024 (EMNLP).

Fantastic experience presenting this research on LLMs at the University of Bath's "Impact in Action" event! More about the Event: bath.ac.uk/events/impact-… #NLProc #LLMs #AI

📣 Calling all domain experts and researchers working on interdisciplinary areas x #AI #NLP #LLMs Do you think AI can be taught to comply with standards, regulations, and norms across various domains (science, engineering, health, etc)? 🤔 We need your insights! Participate in

Domain experts in the sciences, education, engineering, and healthcare are driven by standards and regulations. Is it time for AI to learn these standards for wider, more trusted adoption across domains? 🤔 Share your insights using the survey below: 🔗

We might be a small NLP lab, but we pack a punch in research productivity! 🚀 With 14 published papers for 2024, we thank our academic and industry collaborators, and our lab PI and PhD students for their amazing efforts!💚 Here's to more groundbreaking research for 2025! 🎉

How do humans and LLMs really learn language? Dive into Construction Grammar (CxG)'s perspective on language model capabilities at our #COLING2025 Tutorial! Happening tomorrow @ Capital Suite 7 from 14:00 - 17:30 PM #NLProc Co-organized by our Lab PI Harish Tayyar Madabushi 👨‍🏫

Excited to be at COLING 2025! Looking forward to meeting collaborators in person and sharing our work. Here Melissa and I from BathNLP.

Happening at 2pm! Join us at the COLING 2025 tutorial: Bridging Linguistic Theory and AI: Usage-Based Learning in Humans and Machines sites.google.com/view/linguisti… with James Pustejovsky James Pustejovsky Nikhil Krishnaswamy and Claire Bonial #coling2025 #nlproc #tutorial

Thank you so much to Vilém Zouhar and Joseph Imperial for two fantastic presentations in the last Cardiff NLP seminars! 🙏 "NLG evaluation" and "LLM alignment for regulatory compliance" were the topics of each of the talks.

It’s finally here! 🥳

I'll be attending #AAAI2025 Doctoral Consortium in Philadelphia 🇺🇸 next week to present my current PhD research on controlling NLG for standard alignment. Happy to chat or meet up! I don't know what Philly is like so if you have recommendations (food or places) I'd love to hear

One of the largest NLP meetups in Cardiff and UK! Open to all NLP researchers 📢

In London attending the AI Standards Hub Global Summit organized by The Alan Turing Institute. I’m also excited to share that I joined the British Standards Institution (BSI UK) 🇬🇧—the UK’s national standards body—as a committee member for the AI working group ART/1 and will work with

Great to hear from Joseph Imperial, an AAAI / ACM SIGAI doctoral consortium participant and PhD student at University of Bath. He told us about his research aligning generative AI with technical standards aihub.org/2025/04/02/int…

This has been accepted to ACL2025 (Main) 🥳 Happy to have contributed so much to this project, along with my amazing collaborators at SEACrowd !

Is In-Context Learning (ICL) in LLMs Memorisation? Emergence? Some Algorithmic Capability? 🤔 📢New work exploring ICL in LLMs: arxiv.org/abs/2505.11004 💡Key Finding: ICL capabilities are linked to token frequency 🤨 Strap in for the unexpected 🤯 A 🧵👇 #NLProc #LLMs

🚨 New global collaboration & dataset paper! UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment 🌍 We introduce UniversalCEFR, an initiative to build a growing, open, multilingual, and multidimensional resource for CEFR-based language