Ishika Agarwal (@wonderingishika) 's Twitter Profile
Ishika Agarwal

@wonderingishika

PhD @IllinoisCDS | Data Efficient NLP | @convai_uiuc

ID: 721883724879499264

linkhttp://agarwalishika.github.io calendar_today18-04-2016 02:11:06

78 Tweet

302 Followers

1,1K Following

Priyanka Kargupta (@priyanka_karg) 's Twitter Profile Photo

Tree-structured debates between LLM agents elicit critical, comparative reasoning. Tree-of-Debate transforms scientific papers into personas that debate their novelties to identify unique and similar ideas. Paper: arxiv.org/abs/2502.14767 w/ Ishika Agarwal Tal August Data Mining Group@UIUC!

Tree-structured debates between LLM agents elicit critical, comparative reasoning. Tree-of-Debate transforms scientific papers into personas that debate their novelties to identify unique and similar ideas.

Paper: arxiv.org/abs/2502.14767 w/ <a href="/wonderingishika/">Ishika Agarwal</a> <a href="/tal_august/">Tal August</a> <a href="/dmguiuc/">Data Mining Group@UIUC</a>!
Bowen Jin (@bowenjin13) 's Twitter Profile Photo

🚀 Introducing 𝗦𝗲𝗮𝗿𝗰𝗵-𝗥𝟭 – the first 𝗿𝗲𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗗𝗲𝗲𝗽𝘀𝗲𝗲𝗸-𝗥𝟭 (𝘇𝗲𝗿𝗼) for training reasoning and search-augmented LLM agents with reinforcement learning! This is a step towards training an 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗢𝗽𝗲𝗻𝗔𝗜 “𝗗𝗲𝗲𝗽

Vilém Zouhar (@zouharvi) 's Twitter Profile Photo

Panopticon, but instead of prison cells, it's a stack of Overleaf tabs. You can’t watch them all at once, but at any moment, you *could* be watching any of them. And they know it.

Panopticon, but instead of prison cells, it's a stack of Overleaf tabs. You can’t watch them all at once, but at any moment, you *could* be watching any of them. And they know it.
Isha Chaudhary (@ish_cha_) 's Twitter Profile Photo

#ICLR2025 was a blast! Grateful for the opportunity to present our work on formally certifying LLMs. For more details of our work, please check out our project page: certifyllm.com

#ICLR2025 was a blast! 
Grateful for the opportunity to present our work on formally certifying LLMs. For more details of our work, please check out our project page: certifyllm.com
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]
Beyza Bozdag @ NAACL’25 (@nbbozdag) '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!✨ Ishika Agarwal 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="/wonderingishika/">Ishika Agarwal</a> and I are excited to announce our newest preprint in which we explore “Language Specific Knowledge (LSK)”.