Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification

K Thompson, N Saavedra, P Carrott, K Fisher… - arxiv preprint arxiv …, 2024 - arxiv.org
Formal verification using proof assistants, such as Coq, enables the creation of high-quality
software. However, the verification process requires significant expertise and manual effort …

Can Transformers Do Enumerative Geometry?

B Hashemi, RG Corominas, A Giacchetto - arxiv preprint arxiv …, 2024 - arxiv.org
How can Transformers model and learn enumerative geometry? What is a robust procedure
for using Transformers in abductive knowledge discovery within a mathematician-machine …

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation

C An, S Imani, F Yao, C Dong, A Abbasi… - arxiv preprint arxiv …, 2024 - arxiv.org
In the field of large language model (LLM)-based proof generation, despite being trained on
extensive corpora such as OpenWebMath and Arxiv, these models still exhibit only modest …

Synthetic Theorem Generation in Lean

J Rotella, Z Qin, AZH Yang, B Miranda, MEA Seddik… - openreview.net
The application of large language models (LLMs) to theorem proving presents a promising
avenue for advancing formal mathematics. Interactive theorem provers, such as Lean, offer a …