pith. sign in

Proof artifact co-training for theorem proving with language models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2024 1 2023 1

verdicts

UNVERDICTED 2

representative citing papers

ImProver: Agent-Based Automated Proof Optimization

cs.AI · 2024-10-07 · unverdicted · novelty 7.0

ImProver is an LLM agent using Chain-of-States, error-correction, and retrieval to rewrite Lean proofs for arbitrary user-defined optimization criteria like shortness and readability.

Llemma: An Open Language Model For Mathematics

cs.CL · 2023-10-16 · unverdicted · novelty 6.0

Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.

citing papers explorer

Showing 2 of 2 citing papers.

  • ImProver: Agent-Based Automated Proof Optimization cs.AI · 2024-10-07 · unverdicted · none · ref 11

    ImProver is an LLM agent using Chain-of-States, error-correction, and retrieval to rewrite Lean proofs for arbitrary user-defined optimization criteria like shortness and readability.

  • Llemma: An Open Language Model For Mathematics cs.CL · 2023-10-16 · unverdicted · none · ref 146

    Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.