Hear me out: What if the Chinese translations of mathematical problems present in English test sets (e.g. MATH) were not filtered from the pre-training corpora of Qwen and DeepSeek? this means the knowledge is there, just translated. This would also explain the language switching when RL-ing CoT 👇
10.02.2025 15:51 — 👍 7 🔁 2 💬 1 📌 0
Me
19.11.2024 03:18 — 👍 1 🔁 0 💬 0 📌 0
Professor of Statistical Machine Learning at the University of Adelaide.
https://sejdino.github.io/
Assistant Professor of Machine Learning
Generative AI, Uncertainty Quantification, AI4Science
Amsterdam Machine Learning Lab, University of Amsterdam
https://naesseth.github.io
Asst. Prof. in Machine Learning at UofT. #LongCOVID patient.
https://www.cs.toronto.edu/~cmaddis/
Theory & practice of probabilistic programming. Current: MIT Probabilistic Computing Project; Fall '25: Incoming Asst. Prof. at Yale CS
Assoc. Prof in CS @ Northeastern, NLP/ML & health & etc. He/him.
Incoming Asst Prof @UMD Info College, currently postdoc @UChicago. NLP, computational social science, political communication, linguistics. Past: Info PhD @UMich, CS + Lx @Stanford. Interests: cats, Yiddish, talking to my cats in Yiddish.
PhD @ MIT. Prev: Google Deepmind, Apple, Stanford. 🇨🇦 Interests: AI/ML/NLP, Data-centric AI, transparency & societal impact
Asst prof @ University of Utah · NLP · she/her 🇭🇷
CS PhD candidate at Columbia. NLP & Computational Social Science. NSF GRFP fellow. he/him. https://skywang.me
PhD student @ ETH Zürich | all aspects of NLP but mostly evaluation and MT | go vegan | https://vilda.net
assistant professor @ interacting minds centre, aarhus university 🇩🇰 || nlp, cognition, datasci 🗣️ 🧠 🤖 || previously: postdoc @ UT Austin 🤘 & data fellow @ UN humdata 🇺🇳
https://faculty.washington.edu/aylin
Computer scientist • Prof @UWischool & @UWcse
Co-Director @TechPolicyLab • Nonresident Senior Fellow @BrookingsInst
AI & Societal Impacts: Ethics in NLP • Multimodal ML • CV • Human-AI Collaboration
phd @ cornell infosci
https://andreawwenyi.github.io
PhD candidate @ Stanford NLP
https://myracheng.github.io/
PhDing at LTI, CMU
Prev: Ai2, Google Research, MSR
Evaluating language technologies, regularly ranting, and probably procrastinating.
https://sites.google.com/view/shailybhatt/
Associate Professor (Linguistics) at University of Washington
https://shane.st
Assistant Professor confused by the concept of consciousness but talkingtorobots.com in the meantime
PhD student, University of Copenhagen
NLP, misinformation, media framing, hatespeech, cultural values, CSS, Pol Comm, AI ethics |
he/him.
https://scholar.google.com/citations?user=EQUUUUoAAAAJ&hl=en
NLP and computational social science (CSS) researcher. Assistant Professor in Computer Science at Williams College. AI2 and UMass Amherst alum. she/her. https://kakeith.github.io/