🔥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

We continue with our first oral presentation of the day, with Stefan Arnold presenting their work on "Routing in Sparsely-gated Language Models responds to Context" aclanthology.org/2024.blackboxn…

I’m giving a talk about this paper today in the 3- 3:30 session BlackboxNLP (Jasmine ballroom) and will stick around for the afternoon poster session as well. Would love to hear your opinions 😊

After an inspiring keynote by 𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞, we continue with an oral presentation by Tom Lieberum 🔸 on "Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2" aclanthology.org/2024.blackboxn…

We wrap up the day with a panel on the state of interpretability with 4 fantastic panellists: Jack Merullo, Dieuwke Hupkes, Marius Mosbach and Vera Liao!

Panel discussion at blackboxNLP with Jack Merullo Dieuwke Hupkes Marius Mosbach Vera Liao moderated by Hanjie Chen #EMNLP2024 BlackboxNLP

🚀✨ Our Political-LLM is now live on arXiv! ✨🚀 🤝 A collaboration of 40+ researchers across ML and PoliSci exploring how LLMs are revolutionizing political science research 🔗 arxiv.org/abs/2412.06864 #AI #PoliticalScience #LLM #ML

Re: “Every major breakthrough in AI has been American”: America does itself no favors when it overestimates its specialness. Yes, the center of the AI industry is the US (California!), but many of the breakthroughs of (neural, gradient-based) AI happened elsewhere: • LSTMs,

How do LLMs work? What is it about the recently-announced DeepSeek technology that has changed the way people think about building large AI models? Join us for the answers to these questions and more. Co-sponsored by Rice CS & The Ken Kennedy Institute. RSVP: RiceGenAI.eventbrite.com

Haotian did amazing work during his visit to my lab Rice Computer Science. He’s a special student with a background in both CS and Sports (as a former NCAA Division I student-athlete🏐) He introduced me to the AI for Sports area, and I’m excited to explore more with him moving forward!🏃‍♀️

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work? We propose 😎 𝗠𝗜𝗕: a Mechanistic Interpretability Benchmark!

Please check @ChangRuidi53250's work using a small inference network to control the learning behavior of LMs. Talk to her if you are also at #NAACL2025! 😃😃😃

My student Ruidi Chang will present her first work "SAFR: Neuron Redistribution for Interpretability" at #NAACL2025✨🥳 📍Hall 3, Session B: Oral/Poster 1, Wednesday 4/30/2025, 11:00-12:30 Come and say hi~👋

Happy to announce that we (w/ my student Daking Rai ) will present a tutorial on 𝐌𝐞𝐜𝐡𝐚𝐧𝐢𝐬𝐭𝐢𝐜 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐟𝐨𝐫 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬! Look forward to meeting people ICML Conference Stay tuned! ziyu-yao-nlp-lab.github.io/ICML25-MI-Tuto… George Mason University Department of Computer Science - George Mason

Since people have been asking - the #blackboxNLP workshop will return this year, to be held with #emnlp2025. This workshop is all about interpreting and analyzing NLP models (and yes, this includes LLMs). More details soon, follow BlackboxNLP

BlackboxNLP will be co-located with #EMNLP2025 in Suzhou this November! 📷This edition will feature a new shared task on circuits/causal variable localization in LMs, details: blackboxnlp.github.io/2025/task If you're into mech interp and care about evaluation, please submit!

🥳We are organizing a workshop at COLM to discuss the research gap about applying explainability/interpretability to enhance LLMs in challenging reasoning and planning tasks! Check out our tentative schedule at …reasoning-planning-workshop.github.io **Submit your excellent work to us!**

🎓🎉🥳🐦🔜🦉💙