wellecks / llemma_formal2formal
Llemma formal2formal (tactic prediction) theorem proving experiments
☆16Updated last year
Related projects ⓘ
Alternatives and complementary repositories for llemma_formal2formal
- The official repository for the paper Multilingual Mathematical Autoformalization☆32Updated 5 months ago
- NaturalProver: Grounded Mathematical Proof Generation with Language Models☆34Updated last year
- This is the official repository for all the code of TheoremLlama☆30Updated 3 weeks ago
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆18Updated 5 months ago
- Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"☆17Updated last year
- Harmonic Datasets☆32Updated 3 months ago
- ☆18Updated 2 months ago
- AI for Mathematics Paper List☆13Updated this week
- Code & data for ICLR 2024 spotlight paper: 🍯MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data☆36Updated 5 months ago
- ☆17Updated this week
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆45Updated last week
- 🔗 LINC: Logical Inference via Neurosymbolic Computation [EMNLP2023]☆55Updated 10 months ago
- Scripts for downloading and pre-processing the `proof-pile`, a high quality dataset of mathematical text and code.☆18Updated last year
- An updated version of miniF2F with lots of fixes and informal statements / solutions.☆65Updated 5 months ago
- llmstep: [L]LM proofstep suggestions in Lean 4.☆118Updated 11 months ago
- The is the official implementation of "Lyra: Orchestrating Dual Correction in Automated Theorem Proving"☆12Updated 4 months ago
- The Lean Theorem Proving Environment☆13Updated last year
- Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs☆34Updated 8 months ago
- PyTorch code for the RetoMaton paper: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022)☆71Updated 2 years ago
- ☆21Updated last month
- A framework for few-shot evaluation of autoregressive language models.☆23Updated 10 months ago
- [EMNLP 22] UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression☆26Updated last year
- Code for the paper LEGO-Prover: Neural Theorem Proving with Growing Libraries☆53Updated 8 months ago
- Scratchpad/Chain-of-Thought Prompts☆12Updated 2 years ago
- ☆27Updated last week
- ☆13Updated 2 months ago
- [EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation☆43Updated 10 months ago
- Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving☆37Updated last year
- Code for the paper: Proving Theorems Recursively☆11Updated 5 months ago
- ☆75Updated last month