How can we help LLMs move beyond the obvious toward generating more creative and diverse ideas? In our new TACL paper, we propose a novel approach to enhance LLM creative generation! https://t.co/AFCpQddN6j @ChenShani2 @GabiStanovsky @jurafsky @HyadataLab @stanfordnlp @nlphuji

New research shows LLMs favor compression over nuance — a key reason they lack human-like understanding. By Stanford postdoc @ChenShani2, CDS Research Scientist @ziv_ravid, CDS Founding Director @ylecun, & Stanford professor @jurafsky. https://t.co/MrsXLtzaw8

You know all those arguments that LLMs think like humans? Turns out it's not true. 🧠 In our paper "From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning" we test it by checking if LLMs form concepts the same way humans do @ylecun @ChenShani2 @jurafsky

@ylecun and I have been pondering the concept of optimal representation in self-supervised learning, and we're excited to share our findings in a recently published paper! 📝🔍

@stanfordnlp

At NAACL?? I'm presenting "Rethinking Word Similarity: Semantic Similarity through Classification Confusion" at 4:15 pm today (Ruidoso room) @KaitlynZhou @danedels @jurafsky Human-inspired measure of semantic similarity with cool real-world applications! https://t.co/TLpretE400

🚨🚨New Working Paper🚨🚨 AI-generated content is getting more politically persuasive. But does labeling it as AI-generated change its impact?🤔 Our research says the disclosure of AI authorship has little to no effect on the persuasiveness of AI-generated content. 🧵1/6

#ELSCspecialseminar with Dr. Chen Shani on the topic of “Designing Language Models to Think Like Humans” will take place on Tuesday, June 25, at 14:00 IST. Come hear the lecture at ELSC: Room 2004, Goodman bldg. @ChenShani2

Stanford NLP Retreat! It was a packed weekend, full of great people and activities (And the car broke down halfway back, another great adventure!)

Stanford NLP Retreat 2024! @RyanCLouie and I organized a PowerPoint Karaoke 🎤 My favorite part is Chris' answer: Q: What is the first principle component for both babies and undergrads? Chris Manning: HUNGER! @ChrisManning @stanfordnlp

One of the T-shirts I designed and printed as a farewell gift for my PhD supervisor (this is my favorite one)

🚀 Excited to share our latest paper about the sensitivity of LLMs to prompts! https://t.co/rdSkRnmw7l Our work may partly explain why some models seem less accurate than their formal evaluation may suggest. 🧐 @guymkaplan, @malk_dan, @DrorRotem, @HyadataLab, @GabiStanovsky

The language people use when they interact with each other changes over the course of the conversation. 🔍 Will we see a systematic language change along the interaction of human users with a text-to-image model? #EMNLP23 https://t.co/wsjb42l2Xd W @LChoshen @AbendOmri 🧵👇

Excited to share our new @biorxivpreprint presenting DISCOVER, a generalized method toward systematic visual interpretability of image-based classification models! Project led by @oded_rotem in collaboration with @AiVFtech! https://t.co/nFbxRh108P 🧵 1/n

[1/9] 🚨 We present our recent @GoogleAI project: The Chosen One --- a fully automated solution for the task of consistent character generation in text-to-image diffusion models 🧑‍🎨. Project Page: https://t.co/JfMvAfnrad

🎉Excited to announce our paper's acceptance at #EMNLP2023! We explore a fascinating question: When faced with (un)answerable queries, do LLMs actually grasp the concept of (un)answerability?🧐 This work is a collaborative effort with @clu_avi @ravfogel @omerNLP and Ido Dagan 1/n

1. I'm officially a Ph.D! Thank you for everything @HyadataLab! 2. I'll present 2 papers at EMNLP: Towards Concept-Aware LLMs ( https://t.co/4LtTj3JNGc) FAME: Flexible, Scalable Analogy Mappings Engine ( https://t.co/WDOK5GSbec) @drjilles @HyadataLab @HebrewU @HebrewU_heb

2/2 papers submitted to EMNLP'23 have been accepted, should be the highlight of my PhD! But, I can't be happy when there's a war... @emnlpmeeting #IsraelUnderAttack

Humor is a complicated phenomenon relating to culture, context, personal flavor, etc. Contemporary LLMs are impressive, but they are not panacea, especially for such a subjective human trait.

New preprint! Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models Preprint: https://t.co/0ayV4vco7B