Vitaliy Polshkov

cogwheelhead

cogwheelhead

AI & ML interests

Data-centric AI methods; Experiment design, statistical learning and causal inference approaches for LLM / agentic evaluations; "Proper old-school" RL and meta-learning techniques for LLM training

Recent Activity

upvoted a paper 27 days ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

commented a paper 30 days ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

posted an update about 1 month ago

Hey! Me and my team recently released two benchmarks on university-level math: U-MATH (for University-MATH) and μ-MATH (for Meta U-MATH). We're working a lot on complex reasoning for LLMs, and we were in particular interested in evaluating university-curricula math skills — in topics such as differential calculus and linear algebra — for their wide applicability and practicality. We noticed that available benchmarks at the time were either at or below high-school level, or mainly leaning towards Olympiad-style problems, or synthetically generated from a set of templates / seeds. We wanted focus on university curricula and we wanted "organic" variety, so we created our own benchmark using problems sourced from actual teaching materials used in top US universities — that is how U-MATH came to be. We also, and that is my primary focus in particular, are very eager on studying and improving evaluations themselves, since the standard llm-as-a-judge approach is known to be noisy and biased, but that often remains unaccounted for. So we then created a U-MATH-derived benchmark to do "meta-evaluations" — i.e. evaluate the evaluators — which allows to quantify their error-rates, study their behaviors and biases, and so on. I'm super excited to be sharing those publicly! https://huggingface.co./datasets/toloka/u-math https://huggingface.co./datasets/toloka/mu-math

View all activity

Organizations

cogwheelhead's activity

commented a paper 30 days ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published Dec 9, 2024 • 74 •

commented a paper about 1 month ago

U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs

Paper • 2412.03205 • Published Dec 4, 2024 • 16 •