Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
veganism.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Veganism Social is a welcoming space on the internet for vegans to connect and engage with the broader decentralized social media community.

Administered by:

Server stats:

295
active users

veganism.social: AboutStatusPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.0-alpha.5+vegan

#leanprover

11 posts7 participants1 post today
Public
José A. Alonso

Leanabell-prover: Posttraining scaling in formal reasoning. ~ Jingyuan Zhang et als. arxiv.org/abs/2504.06122 #LLMs #ITP #LeanProver

arXiv logo
arXiv.orgLeanabell-Prover: Posttraining Scaling in Formal ReasoningRecent advances in automated theorem proving (ATP) through LLMs have highlighted the potential of formal reasoning with Lean 4 codes. However, ATP has not yet be revolutionized by the recent posttraining scaling as demonstrated by Open AI O1/O3 and Deepseek R1. In this work, we investigate the entire posttraining of ATP, aiming to align it with breakthroughs in reasoning models in natural languages. To begin, we continual train current ATP models with a hybrid dataset, which consists of numerous statement-proof pairs, and additional data aimed at incorporating cognitive behaviors that emulate human reasoning and hypothesis refinement. Next, we explore reinforcement learning with the use of outcome reward returned by Lean 4 compiler. Through our designed continual training and reinforcement learning processes, we have successfully improved existing formal provers, including both DeepSeek-Prover-v1.5 and Goedel-Prover, achieving state-of-the-art performance in the field of whole-proof generation. For example, we achieve a 59.8% pass rate (pass@32) on MiniF2F. This is an on-going project and we will progressively update our findings, release our data and training details.
VegansExploreLive feeds
About