(ACL 2025 Main) Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification - Official Implementation & Dataset
☆21Dec 26, 2025Updated 10 months ago
Alternatives and similar repositories for Safe
Users that are interested in Safe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Suggested conventions and examples for Lean formalization of IMO problem statements☆18Updated this week
- This repository includes code and materials for the paper "Efficient PRM Training Data Synthesis via Formal Verification" (ACL 2026 Findi…☆20Apr 7, 2026Updated 6 months ago
- ☆16Jul 10, 2023Updated 3 years ago
- Code and Data for ACL 2025 Paper "Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework".☆31Oct 3, 2025Updated last year
- ☆45Jul 29, 2026Updated 3 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆20May 14, 2025Updated last year
- The official code release for Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization☆39Mar 9, 2025Updated last year
- Code for Research Project TLDR☆26Jul 28, 2025Updated last year
- Program Analysis, Software Verification & Testing. Python3, CAS, Dafny, Z3, CVC4, UCLID, ZChaff, NuSMV, AFL, Scala, CBMC & LLVM Framework…☆41Apr 9, 2023Updated 3 years ago
- Proof infrastructure about LTL in Lean 4☆40Updated this week
- ☆26Jun 28, 2026Updated 4 months ago
- A Tokio-inspired concurrency library and work-stealing scheduler for Lean 4, with machine-checked proofs.☆33Updated this week
- ☆31Jul 16, 2025Updated last year
- A Dependently Typed Esolang☆10Aug 4, 2017Updated 9 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Released code for「Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction」in EMNLP2023.☆13Mar 28, 2024Updated 2 years ago
- ☆15Jul 21, 2023Updated 3 years ago
- Public code release for "Optimistic Verifiable Training by Controlling Hardware Nondeterminism" (NeurIPS 2024).☆11Oct 25, 2024Updated 2 years ago
- ☆14Jul 24, 2021Updated 5 years ago
- ☆12Mar 23, 2024Updated 2 years ago
- Proof-carrying code completions in Dafny☆11Apr 4, 2025Updated last year
- ☆14Oct 27, 2026Updated last week
- Day 2 of Lambda School's Machine Learning Mini Bootcamp☆10Aug 31, 2018Updated 8 years ago
- Code to support the guide to logical induction for software engineers☆11Jul 12, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Nix + Lean = Nale☆12Jul 16, 2023Updated 3 years ago
- ACL24☆11Jun 7, 2024Updated 2 years ago
- This is the official implementation for MA-LoT.☆21Aug 4, 2025Updated last year
- ☆13Oct 29, 2026Updated last week
- Basic TLA+ Examples☆15Feb 15, 2021Updated 5 years ago
- ☆12Jul 8, 2024Updated 2 years ago
- ☆14Feb 22, 2026Updated 8 months ago
- ☆23Jul 5, 2024Updated 2 years ago
- A minimal language for Isabelle/HOL, designed for easing machine learning.☆33Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- Python tools for the K Framework☆13Apr 25, 2024Updated 2 years ago
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- LibCP -- A Library for Conformal Prediction☆13Feb 26, 2015Updated 11 years ago
- Verifying curve25519-dalek using Lean☆14Updated this week
- [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆25Sep 26, 2024Updated 2 years ago
- ☆11Aug 6, 2024Updated 2 years ago