HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement

arXiv:2505.15740 · cs.FL, cs.AI, cs.SE · Submitted 2025-05-21 · Read on arXiv

cs.FL, cs.AI, cs.SE

Submitted: 2025-05-21

Updated: 2026-08-27

Project page: http://www

Terminology

• Verification — 17× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Ablation Studies — 9× in this paper · explained in 1 episode
• Formal Methods — 7× in this paper · explained in 3 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Formal Verification — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Archive of Formal Proofs — 1× in this paper
• Cooperation — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• SMT solver — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
• Evaluating Large Language Models Trained on Code
• NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
• Diverse Inference and Verification for Advanced Reasoning
• Formal Specifications from Natural Language
• A formal proof of the Kepler conjecture
• A Survey on Large Language Models for Code Generation
• A Mechanised Proof of G\"odel's Incompleteness Theorems using Nominal Isabelle
• Generative Language Modeling for Automated Theorem Proving
• TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
• SubgoalXL: Subgoal-based Expert Learning for Theorem Proving
• Lyra: Orchestrating Dual Correction in Automated Theorem Proving

Related papers

• Positive-Data Learning of Fixed-Observation Linear MCFGs from Working Binary Presentations