Shuhaib Mehri (@shuhaibmehri) 's Twitter Profile
Shuhaib Mehri

@shuhaibmehri

PhD @IllinoisCDS @ConvAI_UIUC | Incoming @IBMResearch | Previously @amazon

ID: 1509199254476132358

linkhttps://shuhaibm.github.io calendar_today30-03-2022 16:02:17

16 Tweet

68 Followers

248 Following

UBC NLP Group (@ubc_nlp) 's Twitter Profile Photo

📢 Check out the accepted EMNLP'23 papers from our UBC NLP group! Congratulations to all the authors and stay tuned for the camera-ready preprints! 🎉 #EMNLP2023 #ubcnlp #NLProc

📢 Check out the accepted EMNLP'23 papers from our UBC NLP group!
Congratulations to all the authors and stay tuned for the camera-ready preprints! 🎉
#EMNLP2023 #ubcnlp #NLProc
Vered Shwartz (@veredshwartz) 's Twitter Profile Photo

Finally, Shuhaib Mehri will present his work on instruction tuning for automatic evaluation of generative tasks (arxiv.org/abs/2310.20072) at the GEM workshop on Wed, Dec 6 at 11am SGT. He is applying to grad schools, talk to him if you're recruiting :) 7/7

Finally, <a href="/ShuhaibMehri/">Shuhaib Mehri</a> will present his work on instruction tuning for automatic evaluation of generative tasks (arxiv.org/abs/2310.20072) at the GEM workshop on Wed, Dec 6 at 11am SGT. He is applying to grad schools, talk to him if you're recruiting :) 7/7
Shuhaib Mehri (@shuhaibmehri) 's Twitter Profile Photo

Excited to virtually attend #EACL2024! I will be presenting my work with Li Chuyuan and carenini giuseppe: "Exploiting Questions Under Discussion for Discourse Relation Recognition in Dialog"

ConvAI@UIUC (@convai_uiuc) 's Twitter Profile Photo

Welcome to the official page of ConvAI@UIUC! 🤖 Based in the cornfields of UIUC, and led by dilek hakkani-tur and Gokhan Tur, we do cool research on chatbots, dialogue, embodied agents, and everything in between!

dilek hakkani-tur (@dilekhakkanitur) 's Twitter Profile Photo

While persuasive models are promising for social good, they can also be misused towards harmful behavior. Recent work by Beyza Bozdag and Shuhaib Mehri aims to assess LLM persuasiveness and susceptibility towards persuasion.

Sumuk (@sumukx) 's Twitter Profile Photo

we're launching 🤗 yourbench today, an open source tool for custom benchmarking and synthetic data generation from ANY of your documents. it's a big step towards improving how model evaluations work early access link in replies! (1/8)

we're launching 🤗 yourbench today, an open source tool for custom benchmarking and synthetic data generation from ANY of your documents. it's a big step towards improving how model evaluations work

early access link in replies!

(1/8)
Sagnik Mukherjee (@saagnikkk) 's Twitter Profile Photo

🚀Our ICML 2025 paper introduces "Premise-Augmented Reasoning Chains" - a structured approach to induce explicit dependencies in reasoning chains. By revealing the dependencies within chains, we significantly improve how LLM reasoning can be verified. 🧵[1/n]

🚀Our ICML 2025 paper introduces "Premise-Augmented Reasoning Chains" - a structured approach to induce explicit dependencies in reasoning chains. 

By revealing the dependencies within chains, we significantly improve how LLM reasoning can be verified.

🧵[1/n]
Shuhaib Mehri (@shuhaibmehri) 's Twitter Profile Photo

Excited to share our survey on computational persuasion - check it out to learn more about 🤖 AI as Persuader, 🎯AI as Persuadee, and ⚖️AI as Persuasion Judge!

Sagnik Mukherjee (@saagnikkk) 's Twitter Profile Photo

🚨 Paper Alert: “RL Finetunes Small Subnetworks in Large Language Models” From DeepSeek V3 Base to DeepSeek R1 Zero, a whopping 86% of parameters were NOT updated during RL training 😮😮 And this isn’t a one-off. The pattern holds across RL algorithms and models. 🧵A Deep Dive

🚨 Paper Alert: “RL Finetunes Small Subnetworks in Large Language Models”

From DeepSeek V3 Base to DeepSeek R1 Zero, a whopping 86% of parameters were NOT updated during RL training 😮😮
And this isn’t a one-off. The pattern holds across RL algorithms and models.
🧵A Deep Dive
Ishika Agarwal (@wonderingishika) 's Twitter Profile Photo

Would models know more about Indian food in Hindi and Turkey’s history in Turkish? Does the language of a question affect an LLM’s answer? ✨Yes!✨ Beyza Bozdag and I are excited to announce our newest preprint in which we explore “Language Specific Knowledge (LSK)”.

Would models know more about Indian food in Hindi and Turkey’s history in Turkish? Does the language of a question affect an LLM’s answer?

✨Yes!✨

<a href="/nbbozdag/">Beyza Bozdag</a> and I are excited to announce our newest preprint in which we explore “Language Specific Knowledge (LSK)”.