Jonathan Zheng (@jonathanqzheng) 's Twitter Profile
Jonathan Zheng

@jonathanqzheng

Student at the Georgia Institute of Technology. Studying Computer Science with a concentration in Intelligence and Theory. Twitter Developer Account.

ID: 1296927624967720968

linkhttp://jonathanqzheng.github.io calendar_today21-08-2020 21:50:21

14 Tweet

33 Followers

58 Following

Jonathan Zheng (@jonathanqzheng) 's Twitter Profile Photo

This Saturday I will be presenting my first publication at #EMNLP2022: "Stanceosaurus: Classifying Stance Towards Multilingual Misinformation" I introduce a new dataset of multilingual claims to combat misinformation on Twitter. paper: arxiv.org/abs/2210.15954

This Saturday I will be presenting my first publication at #EMNLP2022:
"Stanceosaurus: Classifying Stance Towards Multilingual Misinformation"

I introduce a new dataset of multilingual claims to combat misinformation on Twitter.

paper: arxiv.org/abs/2210.15954
Jonathan Zheng (@jonathanqzheng) 's Twitter Profile Photo

I am at #ACL2024NLP 🇹🇭 this week presenting our paper "NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms" (arxiv.org/abs/2402.12261) Poster: Tue 13th, 4:00-5:30 (Convention Center A1) Let's chat about temporal drift and LLM generalizability capabilities!

Wei Xu (@cocoweixu) 's Twitter Profile Photo

Excited to be in Thailand ☀️😎 🌺🥥 to attend #ACL2024! If you run into my PhD students from Georgia Tech NLP group - Yao Dou Yao Dou, Tarek Naous Tarek Naous, and Jonathan Zheng Jonathan Zheng, please say hi! 👋 Please also say hi to my other collaborators!

Excited to be in Thailand ☀️😎 🌺🥥 to attend #ACL2024!

If you run into my PhD students from Georgia Tech NLP group - Yao Dou <a href="/Yaooo01/">Yao Dou</a>, Tarek Naous <a href="/tareknaous/">Tarek Naous</a>, and Jonathan Zheng <a href="/JonathanQZheng/">Jonathan Zheng</a>, please say hi! 👋    

Please also say hi to my other collaborators!
Ethan Mendes (@ethanmendes3) 's Twitter Profile Photo

🚨New Paper: Better search for reasoning (e.g., web tasks) usually requires costly💰demos/rewards What if we only self-improve LLMs on state transitions—capturing a classic RL method in natural language? Spoiler: It works (⬆️39% over base model) & enables efficient search!🚀 🧵

🚨New Paper: Better search for reasoning (e.g., web tasks) usually requires costly💰demos/rewards

What if we only self-improve LLMs on state transitions—capturing a classic RL method in natural language?

Spoiler: It works (⬆️39% over base model) &amp; enables efficient search!🚀
🧵