Harish Tayyar Madabushi

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

[Harish Tayyar Madabushi @harish]

@josephimperial_ Thanks, Joseph!

[Harish Tayyar Madabushi @harish]

Happy to share that I’ve been promoted to Senior Lecturer in AI at the University of Bath (equivalent to Associate Professor).

Grateful to colleagues, mentors, collaborators and students for all the support along the way.

@UniofBath @BathNLP

[Harish Tayyar Madabushi @harish]

@yoavgo I like to use “Context-Directed
Extrapolation”

https://t.co/yr5qk5Qtkl

[Harish Tayyar Madabushi @harish]

@neshkatrapati @LAWeissweiler Replied now! Sorry I missed that message

[Jingcheng (Frank) Niu @frankniujc]

Hey this is me!
Our paper: Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs

Blog post: https://t.co/x6pRVJhSHt

[Haritz Puerto @HaritzPuerto]

I’ll be presenting today at 11:00 in hall x5 booth 209 #ACL2025NLP come and let’s talk about how to train with CoTs!

[Haritz Puerto @HaritzPuerto]

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!
🗓️ Wednesday 30th
🕦11:00
📍Level 1 1.86
https://t.co/EHTYYSuBqw

[Harish Tayyar Madabushi @harish]

@HaritzPuerto @UKPLab @BathNLP @IGurevych We provide open access to our code, models, data, and results:

📽️Underline: https://t.co/fEbrjBXa9l
📄Paper: https://t.co/RNZbxSMPMX
💻 Code: https://t.co/MlmCFA40Rz
🤗 Models: https://t.co/6bDBxQT84O
📂 Data: https://t.co/XJoB8F1FXB
🌐 Website: https://t.co/gdUIWuK0om

(9/🧵)

[Harish Tayyar Madabushi @harish]

At first I was not sure🤔, but on second thought, I knew what to do!!!💡😃

📢 Diverse Chains of Thought help LLMs refine their Reasoning!!

@haritzpuerto will be presenting our work at #ACL2025NLP 🇦🇹 on Wednesday 30th at 11:00

#NLProc

A 🧵👇

[Harish Tayyar Madabushi @harish]

@HaritzPuerto @UKPLab @BathNLP @IGurevych We also observed that when we generate 3 CoTs, if the first 2 CoTs are ❌ and the 3rd is ✅, the model picks the last one! 🎉

This shows that DCoT is not an ensemble of CoTs and instead is doing self-correction 🎊

8/🧵

[Fernando Alva-Manchego @feralvam]

The trial data has just been released to registered participants. There’s still time for your team to join! #emnlp2025 #nlproc

[Harish Tayyar Madabushi @harish]

📢Job Opportunity
Research Associate for Reasoning in LLMs, University of Bath, UK (Deadline 05 August 2025)

We are looking to hire a highly motivated researcher to work on analysing reasoning in LLMs

For more information, see: https://t.co/2bYI0RglSl

[Nedjma Ousidhoum نجمة أوسيدهم @nedjmaou]

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!

[Steven Schockaert @StevenSchockae2]

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: https://t.co/3yLx5WOviV (deadline 21st July)
@Cardiff_NLP @cardiff_krr