
Senior Lecturer (Associate Professor) in Artificial Intelligence. Work on NLP (#NLProc) and Large Language Models
Bath, England
Joined December 2008
- Tweets1.8K
- Following1.5K
- Followers1.8K
- Likes2.6K
BathNLP will be presenting four full papers at #๐๐ ๐ก๐๐ฃ๐ฎ๐ฌ๐ฎ๐ฒ ๐
Our work covers a wide range of topics, from multilingual translation and linguistic grounding to text complexity and standards compliance.
See our full list of papers below!
Harish Tayyar Madabushi retweeted
To welcome you back to school, it's time for a new release of Speech and Language Processing! Our August 2026 edition finally has a chapter 1! Check it out here: web.stanford.edu/~jurafsky/sโฆ
Harish Tayyar Madabushi retweeted
๐ข Call for reviewers! We're organizing PALM, a #NeurIPS2026 workshop on memory for AI systems, in Paris ๐ซ๐ท and we'd love your help!
Have โฅ1 paper at a major ML conference? Pls sign up๐
๐ palm-neurips-2026.github.io
๐ Register: forms.gle/QeVHzqjr7CkN5o777
Harish Tayyar Madabushi retweeted
Hey this is me!
Our paper: Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
Blog post: frankniujc.github.io/publicaโฆ
Harish Tayyar Madabushi retweeted
Iโll be presenting today at 11:00 in hall x5 booth 209 #ACL2025NLP come and letโs talk about how to train with CoTs!
At first I was not sure๐ค, but on second thought, I knew what to do!!!๐ก๐
๐ข Diverse Chains of Thought help LLMs refine their Reasoning!!
@haritzpuerto will be presenting our work at #ACL2025NLP ๐ฆ๐น on Wednesday 30th at 11:00
#NLProc
A ๐งต๐
Harish Tayyar Madabushi retweeted
Excited to present Diverse Chains of Thought at #ACL2025NLP
Do you have a dataset with more than one CoT/question? Do you want to train with that? Come to our poster to see how to make the most out of your data!
๐๏ธ Wednesday 30th
๐ฆ11:00
๐Level 1 1.86
underline.io/events/485/postโฆ
At first I was not sure๐ค, but on second thought, I knew what to do!!!๐ก๐
๐ข Diverse Chains of Thought help LLMs refine their Reasoning!!
@haritzpuerto will be presenting our work at #ACL2025NLP ๐ฆ๐น on Wednesday 30th at 11:00
#NLProc
A ๐งต๐
Harish Tayyar Madabushi retweeted
The trial data has just been released to registered participants. Thereโs still time for your team to join! #emnlp2025 #nlproc
๐ข Call for Participation: TSAR 2025 Shared Task ๐ข
Simplify English paragraphs to a specified CEFR level
๐น No training data
๐น Eval: CEFR match, meaning preservation, ref similarity
๐๏ธ Starts July 16
๐ Info + registration: tsar-workshop.github.io/sharโฆ
#EMNLP2025 #TextSimplification
Harish Tayyar Madabushi retweeted
The Cardiff #NLProc Workshop starts on Monday!
If you've registered, you should have received a confirmation email (from me). Check your spam folder if not, or feel free to get in touch.
Looking forward to seeing many of you in Cardiff!
๐ The Cardiff NLP Workshop kicks off this Monday (14 July)!
Check out the full schedule on our website ๐ cardiffnlpworkshop.org/schedโฆ
Weโve got an exciting lineup:
โจ Talks by fantastic speakers
๐ป A tutorial on steering vectors
๐ผ๏ธ Poster session and networking opportunities
๐ An interdisciplinary session
๐ฌ A panel discussion
Looking forward to welcoming you to Cardiff!
Harish Tayyar Madabushi retweeted
I am looking for a postdoctoral research associate to work on (LLM-based and neurosymbolic) reasoning for story understanding, as part of the EPSRC-funded ReStoRe project. Details: jobs.ac.uk/job/DNS820/researโฆ (deadline 21st July)
@Cardiff_NLP @cardiff_krr
Harish Tayyar Madabushi retweeted
Happy to announce our journal paper on tongue twisters, Train and Constrain (TwistList 2.0), has now been officially published in @CompLingJournal! (Thanks to @chenghua_lin and Chen Tang) direct.mit.edu/coli/article/โฆโฆ @sltcdt #nlp #nlproc #nlg
Harish Tayyar Madabushi retweeted
๐จ New global collaboration & dataset paper!
UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment ๐
We introduce UniversalCEFR, an initiative to build a growing, open, multilingual, and multidimensional resource for CEFR-based language proficiency assessment.
๐ Project Website: universalcefr.github.io/
๐ Paper: arxiv.org/abs/2506.01419
๐ HF Org & Data: huggingface.co/UniversalCEFR
๐ Github: github.com/UniversalCEFR
Harish Tayyar Madabushi retweeted
Have you contributed to developing of local clinical guidelines? Could we interview you?
Keen to talk to anyone, esp. primary care or non-pharmacy professions (including managers etc) - please share with colleagues.
Find out more & volunteer: bit.ly/43ArtiE
Harish Tayyar Madabushi retweeted
Working on RAG? Come check out our InspectorRAGet DEMO presented by @SivaSankalp May 2 (Friday), 11-12:30 at Demo Session 8 in Hall 3! Looking forward to attending ACL in a few months! #NAACL2025 @naaclmeeting
paper: arxiv.org/abs/2404.17347
github: github.com/IBM/InspectorRAGeโฆ
Harish Tayyar Madabushi retweeted
Our @Cardiff_NLP team and collaborators have been releasing amazing NLP models and datasets over the last few years. We've now organised the content as @huggingface collections ๐ค
A short thread summarising some of these NLP resources, in particular related to social media! ๐งต
Harish Tayyar Madabushi retweeted
In London attending the AI Standards Hub Global Summit organized by @turinginst.
Iโm also excited to share that I joined the British Standards Institution (@BSI_UK) ๐ฌ๐งโthe UKโs national standards bodyโas a committee member for the AI working group ART/1 and will work with CEN-CENELECโs Joint Task Force 21. This is the working group in-charge of developing standards for the EU AI Act.
Harish Tayyar Madabushi retweeted
๐ฏToday we release HD-EPIC๐ฏ A new highly detailed egocentric video dataset. Check out Dima's thread below and visit hd-epic.github.io/ to learn more about the dataset
๐๐ข
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
hd-epic.github.io
arxiv.org/abs/2502.04144
New collected videos
263 annotations/min: recipe, nutrition, actions, sounds, 3D object movement &fixture associations, masks.
26K VQA benchmark to challenge current VLMs
1/N
Harish Tayyar Madabushi retweeted
๐ฃ 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)? ๐ค
We need your insights! Participate in our survey to help shape the future of standard-compliant AI systems:
๐ forms.office.com/e/eWAaGsqBZโฆ
โ๏ธ 12-15 mins
๐ค There is also an opportunity to collaborate at the end of the survey if you are interested in updates of the study.
@BathNLP @ARTAIBath
Harish Tayyar Madabushi retweeted
there are many smart speakers and thinkers around AI/ML and/or NLP. but i find almost everything to be kinda predictable by now, minor stylistic variations on the same story. who are some *interesting* speakers i should listen/read? i want things that may surprise or inspire me.
Harish Tayyar Madabushi retweeted
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! ๐


































