Nishant Subramani@ACL🇦🇹
@nsubramani23
PhD student @LTIatCMU working on model interpretability; student researcher @google // Prev: intern @msftresearch, predoc @allen_ai // @BVB supporter // he/him
Excited to announce that I'll be starting my PhD at @LTIatCMU this Fall working on generation and controlling LMs 🥳! Big thank you to my mentors + letter writers @mmitchell_ai, @_DougDowney and @mattthemathman and all my collaborators at @allen_ai for their invaluable support ❤️
At #ACL2025 in Vienna 🇦🇹 till next Saturday! Love to chat about anything #interpretability 🔎, understanding model internals 🔬, and finding yummy vegan food 🥬
At #ICML2025 till Sunday! Love to chat about #interpretability, understanding model internals, and finding yummy vegan food in Vancouver 🥬🍜
🚨New #interpretability paper with @nsubramani23 :🕵️Model Internal Sleuthing: Finding Lexical Identity and Inflectional Morphology in Modern Language Models
🚨 Check out our new #interpretability paper: 🕵🏽 Model Internal Sleuthing led by the amazing @bearseascape who is an undergrad at @SCSatCMU @LTIatCMU!
🚨New #interpretability paper with @nsubramani23 :🕵️Model Internal Sleuthing: Finding Lexical Identity and Inflectional Morphology in Modern Language Models
Excited to announce that I started at @googlecloud as a student researcher last month working with @hamidpalangi on actionable #interpretability 🔍 to build better tool using #agents ⚒️🤖
Presenting this today at the poster session at #NAACL2025! Come chat about interpretability, trustworthiness, and tool-using agents! 🗓️ - Thursday May 1st (today) 📍 - Hall 3 🕑 - 200-330pm
🚀 Excited to share a new interp+agents paper: 🐭🐱 MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools appearing at #NAACL2025 This was work done @Microsoft last summer with @adveisner @justinsvegliato @ben_vandurme @ysu_nlp @sammthomson 1/🧵
At #NAACL2025 🌵till Sunday! Love to chat about interpretability, understanding model internals, and finding vegan food 🥬
🚀 Excited to share a new interp+agents paper: 🐭🐱 MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools appearing at #NAACL2025 This was work done @Microsoft last summer with @adveisner @justinsvegliato @ben_vandurme @ysu_nlp @sammthomson 1/🧵
Building/customizing your own LLM? You'll want to curate training data for it, but how do you know what makes the data good? You can try out recipes👩🍳 iterate on vibes✨ but we can't actually test all possible combos of tweaks,,, right?? 🙅♂️WRONG! arxiv.org/abs/2410.15661 (1/n) 🧵
Wondering how long it takes to train a 1B-param LM from scratch on your GPUs? 🧵 See our paper to learn about the current state of academic compute and how to efficiently train models! Use our code to test your own models/GPUs! arxiv.org/abs/2410.23261 github.com/apoorvkh/acade…