🔥Thrilled to introduce HypoGeniC: Hypothesis Generation with Large Language Models 🔥 How can LLMs systematically propose and verify hypotheses based on observations for #ScientificDiscovery? Read our paper to find out! 📄: arxiv.org/abs/2404.04326… Details in 🧵 (1/n):

🔥🔥🔥 Check out our new paper: Modeling Empathetic Alignment in Conversation, soon to appear at #NAACL2024. 📜arxiv: arxiv.org/abs/2405.00948

I will be in Rio for #FAccT2024 next week. Hit me up if you will also be there in person and would like to chat!🏖️🍻😎

Even ChatGPT knows. It is very hard to think of a positive spin for Rosalind here. A shocking display of ignorance and arrogance.

Just got accepted to NAACL!

1/n You may know that large language models (LLMs) can be biased in their decision-making, but ever wondered how those biases are encoded internally and whether we can surgically remove them?

🚀🚀🚀Excited to share our latest work: HypoBench, a systematic benchmark for evaluating LLM-based hypothesis generation methods!

CaseSumm is publicly available on HuggingFace! We hope this dataset enables: - Better evaluation of long-context summarization - Research on legal language understanding - Development of more accurate & reliable legal AI tools Dataset: huggingface.co/datasets/Chica… I'll be presenting

I’m going to present at the poster session on Friday morning. Come find me! 😃😃

🚨 New paper alert 🚨 Ever asked an LLM-as-Marilyn Monroe who the US president was in 2000? 🤔 Should the LLM answer at all? We call these clashes Concept Incongruence. Read on! ⬇️ 1/n 🧵

🚨Why can’t Transformers learn multiplication?🧮 Even with billions of params, models struggle with multi-digit multiplication. In our new work, we reverse-engineer two models: a standard fine-tuned (SFT), and an implicit chain-of-thought (ICoT) model to see why. Read on! 1/n 🧵