Harish Tayyar Madabushi (@harish) header
Harish Tayyar Madabushi (@harish) profile picture

Senior Lecturer (Associate Professor) in Artificial Intelligence. Work on NLP (#NLProc) and Large Language Models

Bath, England
Joined December 2008
Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)Photo by Harish Tayyar Madabushi (@harish)
Harish Tayyar Madabushi retweeted
BathNLP will be presenting four full papers at #๐—˜๐— ๐—ก๐—Ÿ๐—ฃ๐Ÿฎ๐Ÿฌ๐Ÿฎ๐Ÿฒ ๐ŸŽ‰ 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!
4
1
9
904
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/sโ€ฆ
9
98
9
469
31,201
Harish Tayyar Madabushi retweeted
๐Ÿ“ข Call for reviewers! We're organizing PALM, a #NeurIPS2026 workshop on memory for AI systems, in Paris ๐Ÿ‡ซ๐Ÿ‡ท and we'd love your help! Have โ‰ฅ1 paper at a major ML conference? Pls sign up๐Ÿ™ ๐Ÿ”— palm-neurips-2026.github.io ๐Ÿ“ Register: forms.gle/QeVHzqjr7CkN5o777
1
6
1
17
5,130
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/publicaโ€ฆ
2
3
1
22
1,770
Harish Tayyar Madabushi retweeted
Iโ€™ll be presenting today at 11:00 in hall x5 booth 209 #ACL2025NLP come and letโ€™s talk about how to train with CoTs!
At first I was not sure๐Ÿค”, but on second thought, I knew what to do!!!๐Ÿ’ก๐Ÿ˜ƒ ๐Ÿ“ข Diverse Chains of Thought help LLMs refine their Reasoning!! @haritzpuerto will be presenting our work at #ACL2025NLP ๐Ÿ‡ฆ๐Ÿ‡น on Wednesday 30th at 11:00 #NLProc A ๐Ÿงต๐Ÿ‘‡
1
2
11
1,309
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! ๐Ÿ—“๏ธ Wednesday 30th ๐Ÿ•ฆ11:00 ๐Ÿ“Level 1 1.86 underline.io/events/485/postโ€ฆ
At first I was not sure๐Ÿค”, but on second thought, I knew what to do!!!๐Ÿ’ก๐Ÿ˜ƒ ๐Ÿ“ข Diverse Chains of Thought help LLMs refine their Reasoning!! @haritzpuerto will be presenting our work at #ACL2025NLP ๐Ÿ‡ฆ๐Ÿ‡น on Wednesday 30th at 11:00 #NLProc A ๐Ÿงต๐Ÿ‘‡
2
23
1,312
Harish Tayyar Madabushi retweeted
The trial data has just been released to registered participants. Thereโ€™s still time for your team to join! #emnlp2025 #nlproc
๐Ÿ“ข Call for Participation: TSAR 2025 Shared Task ๐Ÿ“ข Simplify English paragraphs to a specified CEFR level ๐Ÿ”น No training data ๐Ÿ”น Eval: CEFR match, meaning preservation, ref similarity ๐Ÿ—“๏ธ Starts July 16 ๐Ÿ”— Info + registration: tsar-workshop.github.io/sharโ€ฆ #EMNLP2025 #TextSimplification
4
3
888
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!
๐ŸŽ‰ The Cardiff NLP Workshop kicks off this Monday (14 July)! Check out the full schedule on our website ๐Ÿ‘‰ cardiffnlpworkshop.org/schedโ€ฆ Weโ€™ve got an exciting lineup: โœจ Talks by fantastic speakers ๐Ÿ’ป A tutorial on steering vectors ๐Ÿ–ผ๏ธ Poster session and networking opportunities ๐Ÿ”„ An interdisciplinary session ๐Ÿ’ฌ A panel discussion Looking forward to welcoming you to Cardiff!
4
11
875
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/researโ€ฆ (deadline 21st July) @Cardiff_NLP @cardiff_krr
10
16
1,276
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/โ€ฆโ€ฆ @sltcdt #nlp #nlproc #nlg
2
4
1
9
1,635
Harish Tayyar Madabushi retweeted
๐Ÿšจ New global collaboration & dataset paper! UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment ๐ŸŒ We introduce UniversalCEFR, an initiative to build a growing, open, multilingual, and multidimensional resource for CEFR-based language proficiency assessment. ๐ŸŒ Project Website: universalcefr.github.io/ ๐Ÿ“„ Paper: arxiv.org/abs/2506.01419 ๐Ÿ“€ HF Org & Data: huggingface.co/UniversalCEFR ๐Ÿ“€ Github: github.com/UniversalCEFR
1
9
2
25
2,548
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
2
1
1
392
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 ๐Ÿค— A short thread summarising some of these NLP resources, in particular related to social media! ๐Ÿงต
1
6
21
2,111
Harish Tayyar Madabushi retweeted
In London attending the AI Standards Hub Global Summit organized by @turinginst. Iโ€™m also excited to share that I joined the British Standards Institution (@BSI_UK) ๐Ÿ‡ฌ๐Ÿ‡งโ€”the UKโ€™s national standards bodyโ€”as a committee member for the AI working group ART/1 and will work with CEN-CENELECโ€™s Joint Task Force 21. This is the working group in-charge of developing standards for the EU AI Act.
1
2
20
1,186
Harish Tayyar Madabushi retweeted
One of the largest NLP meetups in Cardiff and UK! Open to all NLP researchers ๐Ÿ“ข
Join our 4th Cardiff NLP Workshop! Expression of interest period now open ๐Ÿ‘‡
2
11
872
Harish Tayyar Madabushi retweeted
๐Ÿ“ฏToday we release HD-EPIC๐Ÿ“ฏ 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
๐Ÿ›‘๐Ÿ“ข 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
1
17
734
Harish Tayyar Madabushi retweeted
๐Ÿ“ฃ 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)? ๐Ÿค” We need your insights! Participate in our survey to help shape the future of standard-compliant AI systems: ๐Ÿ”— forms.office.com/e/eWAaGsqBZโ€ฆ โŒ›๏ธ 12-15 mins ๐Ÿค There is also an opportunity to collaborate at the end of the survey if you are interested in updates of the study. @BathNLP @ARTAIBath
1
6
10
1,152
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.
9
14
89
13,766
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! ๐Ÿ™
1
2
12
1,017