به نظر من اینکه مسیح علی‌نژاد چیزی گفته که اکثرن باهاش مخالفیم اتفاقن قشنگی قضیه‌س. اینکه ما رهبر نداریم که حرفش مقدس باشه و هرچی گفت بدویم دنبالش. از هر کسی چیزی که عقلمون حکم میکنه درسته رو برمی‌داریم و میریم جلو. #مهسا_امینی

My alma mater, Sharif University of Technology, Iran's premier university, was under siege yesterday. Many students were arrested, heavily injured or perhaps killed. Many Iranian scholars and PhD students whom you know have received their BSc degrees from this university.

Drago loved his family and was a deeply caring father. His daughter, Victoria has a disability and requires extensive care. We are raising money to help Drago’s family to continue to provide Victoria with the care she needs. Any help will be appreciated!🙏🏼 gofund.me/34bde687

🥳 Super excited at multiple #EMNLP2023 acceptance. Two by my summer interns Apple: Simone Conia on growing multilingual KG and Farima Fatahi Bayat on factual error detection & correction. One with my former colleagues IBM Research on a novel labeling tool. Details coming soon.

Check out our upcoming EMNLP demo paper "FLEEK" (arxiv.org/abs/2310.17119). Tired of inaccurate information? FLEEK can help! This work is done by our intern Farima from UMich and colleagues: Benjamin Han, Yisi Sang Anton Belyi, Samira, Fei Wu, Ihab Ilyas Yunyao Li #emnlp2023

Can we boost chain-of-thought reasoning by guiding decoding toward correct solutions? arxiv.org/abs/2305.14934 Excited to present 🌟GRACE🌟: a guided decoding method that outperforms greedy decoding, self-consistency, and verifiers on math and symbolic reasoning. #EMNLP2023 🧵👇

LLMs often exhibit poorly calibrated confidence, which undermines users' trust in their outputs. Though methods exist for short-form answers, they don't address long-form responses😕 Discover the solution in our #ICLR2024 paper! 📄 arxiv.org/abs/2310.19208 👀

Heard of the Alaska-Hawaii merger?🤔Wonder if LLMs know it’s pending government approval before it can happen? They stumble, but we’ve got a fix⚒️! Dive into my #EMNLP2024 work 𝐍𝐚𝐫𝐫𝐚𝐭𝐢𝐯𝐞-𝐨𝐟-𝐓𝐡𝐨𝐮𝐠𝐡𝐭—a special prompting technique to unlock LLMs’ temporal reasoning

✨I'm on the industry job market!✨ My research focuses on advancing Responsible AI—enhancing the factuality and steerability of AI systems when interacting with users. I'm at #EMNLP2024 🌊 this week and would love to chat about research and career opportunities! more details:

📝When training an LLM, we typically end up with substandard models: they perform best👍on some tasks but worse☹️on others. Should we discard🗑️these models? Well... If you Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs 🧵👇 1/n

🔥 Excited to introduce ManyICLBench (ACL 2025) 🧐 Do many-shot ICL tasks evaluate LCLMs' ability to retrieve the most similar examples or learn from many examples? We carefully analyzed numerous tasks and categorized them. 📄 Paper: arxiv.org/abs/2411.07130 #ACL2025