Undergrads in my class build a trivia-playing robot for their NLP final project. See their systems take on @YogeshRaut15, Yannic Kilcher 🇸🇨, and Victoria Groce on Wednesday! youtu.be/W_8wx9jm_S0

How can we improve benchmarking? The Dynabench experiment aims to make faster progress with dynamic data collection, and today, we are pleased to introduce our next stage: @MetaAI has funded 5 exciting research proposals on the theme of "Rethinking Benchmarking”! Congrats to:

Chain-of-thought (COT) has shown to help LLMs pick correct answers, but can COT reasoning eliminate incorrect answers?🤔 Excited to share the first preprint from my PhD UMD CLIP Lab! 🧵1/5

EMNLP 2023 Best Theme Paper Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition (Sander Schulhoff, Jeremy Pinto et al.) aclanthology.org/2023.emnlp-mai… #EMNLP2023 #NLProc

Amazing work as always coming out of UMD CLIP Lab UMD Department of Computer Science 💪🏽 Huge huge congrats to Sander! Sander Schulhoff Learn Prompting

Shame on me for not posting this earlier than EMNLP2023! 🥴 Ever been baited by video headlines on social media? How do we avoid such misinformation? 🪤This multimodal dataset has human annotations on misleading video headlines and their rationales. 📎arxiv.org/pdf/2310.13859…

Think your QA model can beat a human? 💻👥 Prove it! Submit your model now for our Computer vs Human QA Tournament and let the showdown begin! 🏆 #AITournament #QAChallenge Link: sites.google.com/view/qanta/202…

1⃣Meta’s Cicero by Bakhtin et al. was the talk of town when it was released in November 2022. Even main journals published that Cicero had achieved human-level Diplomacy in strategy and negotiation. Well, had it!? Our paper had this answer: arxiv.org/pdf/2406.04643

I'm bummed that family obligations prevented me from presenting this epic paper. This work represented a long journey for me. I first began working on the language of Diplomacy in 2015, and I struggled for years to get funding to build a bot that could play it ...

I’m super thrilled to have won the AMTA Best Thesis Award!! A huge thanks to the AMTA organizers for this recognition ☺️ See you all in Chicago amtaweb.org

Translation is a complex task involving pre-translation research and post-translation stages. Can #LLMs handle this process step-by-step, relying solely on their internal knowledge? ✨We show that decomposing the translation process significantly improves #Gemini translation