Arkil Patel @arkil.bsky.social · 02/04/2025Thoughtology paper is out!! 🔥🐳 We study the reasoning chains of DeepSeek-R1 across a variety of tasks and find several surprising and interesting phenomena! Incredible effort by the entire team! 🌐: mcgill-nlp.github.io/thoughtology/ 040
Arkil Patel @arkil.bsky.social · 10/03/2025Llamas browsing the web look cute, but they are capable of causing a lot of harm! Check out our new Web Agents ∩ Safety benchmark: SafeArena! Paper: arxiv.org/abs/2503.04957 093
Arkil Patel @arkil.bsky.social · 21/02/2025𝐂𝐇𝐀𝐒𝐄 uses 2 simple ideas: 1. Bottom-up creation of complex context by “hiding” components of reasoning process 2. Decomposing generation pipeline into simpler, "soft-verifiable" sub-tasks 120
Arkil Patel @arkil.bsky.social · 21/02/2025𝐂𝐇𝐀𝐒𝐄 automatically generates challenging evaluation problems across 3 domains: 1. 𝐂𝐇𝐀𝐒𝐄-𝐐𝐀: Long-context question answering 2. 𝐂𝐇𝐀𝐒𝐄-𝐂𝐨𝐝𝐞: Repo-level code generation 3. 𝐂𝐇𝐀𝐒𝐄-𝐌𝐚𝐭𝐡: Math reasoning 120
Arkil Patel @arkil.bsky.social · 21/02/2025Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨ Work w/ fantastic advisors Dima Bahdanau and @sivareddyg.bsky.social Thread 🧵: 1178