https://arxiv.org/abs/2009.03393Generative Language Modeling for Automated Theorem ProvingWe explore the application of transformer-based language models to automated theorem proving. This work is motivated by the possibility that a major limitation of automated theorem provers compared to humans -- the generation of original mathematical terms -- might be addressable via generation from language models. We present an automated prover and proof assistant, GPT-f, for the Metamath formalization language, and analyze its performance. GPT-f found new short proofs that were accepted into the main Metamath library, which is to our knowledge, the first time a deep-learning based system has contributed proofs that were adopted by a formal mathematics community.arxiv.orghttps://arxiv.org/abs/2202.01344Formal Mathematics Statement Curriculum LearningWe explore the use of expert iteration in the context of language modeling applied to formal mathematics. We show that at same compute budget, expert iteration, by which we mean proof search interleaved with learning, dramatically outperforms proof search only. We also observe that when applied to a collection of formal statements of sufficiently varied difficulty, expert iteration is capable of finding and solving a curriculum of increasingly difficult problems, without the need for associated ground-truth proofs. Finally, by applying this expert iteration to a manually curated set of problem statements, we achieve state-of-the-art on the miniF2F benchmark, automatically solving multiple challenging problems drawn from high school olympiads.arxiv.org각각 20년 22년인데 지금 큐스타, 스트로베리가 저거에 기반한 거려나 일단 읽어봐야겠음
저건 metamath기반한거고 알파프루프처럼 lean쓴거볼려면
https://leandojo.org/
이거있음
지금 읽어보는 중인데 22년도껀 meathmath 대신 lean 썼다고 돼있던데 딴 말인가?
맞네뒤에껀lean썻넹 일리야쓴거래서 GPT-f만잇는줄
일리야 또 너야?