🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

At least 1k here at UofM’s Diag, mourning those lost in the mass shooting at MSU. Students laid flowers on the Block M. A banner placed at the bottom of Hatcher’s stairs reads “Wolverines for Spartans”

I just did a poster presentation on my paper “Hi-ToM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models” at the ICML 2023 Theory of Mind Workshop. Nice experience!

1/ New instruction-following dataset INSTRUCT-SKILLMIX! Supervised fine-tuning (SFT) with just 2K-4K (query, answer) pairs gives small “base LLMs” Mistral v0.2 7B and LLaMA3 8B performance rivalling some frontier models (AlpacaEval 2.0 score). No RL, no expensive human data.

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

🤔Now most LLMs have >= 128K context sizes, but are they good at generating long outputs, such as writing 8K token chain-of-thought for a planning problem？ 🔔Introducing LongProc (Long Procedural Generation), a new benchmark with 6 diverse tasks that challenge LLMs to synthesize

AI could be blamed for eliciting suicide attempts😱 Check out my co-first-authored work with Jiahao Qiu and Xinzhe Juan!

Excited to introduce AdaptMI, a test-time adaptation method to provide **minimal**, **targeted** in-context feedback on math reasoning. Shout out to my collaborators Sanjeev Arora Abhishek Panigrahi Yong Lin for pushing my first first-authored project in Princeton!