Image de couverture de livre

SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Su, Xiaole, Zhang, Kasey, Lyu, Andy
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Logic in Computer Science
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Autoformalizing Euclidean Geometry
par: Murphy, Logan, et autres
Publié: (2024)

Munkres' General Topology Autoformalized in Isabelle/HOL
par: Bryant, Dustin, et autres
Publié: (2026)

Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection
par: Lalwani, Abhinav, et autres
Publié: (2024)

Can Large Language Models Autoformalize Kinematics?
par: Kabra, Aditi, et autres
Publié: (2025)

Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks
par: Damera, Sai Sandeep, et autres
Publié: (2026)

Process-Driven Autoformalization in Lean 4
par: Lu, Jianqiao, et autres
Publié: (2024)

ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization
par: Cabral, Rafael, et autres
Publié: (2025)

Abduction of Domain Relationships from Data for VQA
par: Chowdhury, Al Mehdi Saadat, et autres
Publié: (2025)

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
par: Su, DiJia, et autres
Publié: (2024)

Learning Temporal Logic Predicates from Data with Statistical Guarantees
par: Soroka, Emi, et autres
Publié: (2024)

Enhancing Neural Theorem Proving through Data Augmentation and Dynamic Sampling Method
par: Vishwakarma, Rahul, et autres
Publié: (2023)

Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents
par: Brown, Chad E., et autres
Publié: (2026)

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks
par: Zhang, Xiyue, et autres
Publié: (2024)

Scaling the Explanation of Multi-Class Bayesian Network Classifiers
par: Zhang, Yaofang, et autres
Publié: (2026)

Extracting Formulae in Many-Valued Logic from Deep Neural Networks
par: Zhang, Yani, et autres
Publié: (2024)

MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries
par: Xie, Zixuan, et autres
Publié: (2026)

MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
par: Liu, Xinyu, et autres
Publié: (2026)

Conditional Logical Message Passing Transformer for Complex Query Answering
par: Zhang, Chongzhi, et autres
Publié: (2024)

Solving Formal Math Problems by Decomposition and Iterative Reflection
par: Zhou, Yichi, et autres
Publié: (2025)

Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks
par: König, Matthias, et autres
Publié: (2024)

Premise Selection for a Lean Hammer
par: Zhu, Thomas, et autres
Publié: (2025)

Inference of Abstraction for a Unified Account of Reasoning and Learning
par: Kido, Hiroyuki
Publié: (2024)

THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture
par: Li, Augustus Haoyang
Publié: (2026)

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?
par: Taylor, Alexander K, et autres
Publié: (2026)

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
par: Wu, Haoze, et autres
Publié: (2024)

130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?
par: Urban, Josef
Publié: (2026)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
par: Su, DiJia, et autres
Publié: (2025)

MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
par: Pati, Viresh, et autres
Publié: (2026)

Lattice Deduction Transformers
par: Davis, Liam, et autres
Publié: (2026)

Hypergraph Neural Networks Accelerate MUS Enumeration
par: Ijima, Hiroya, et autres
Publié: (2026)

Approximating Pareto Frontiers in Stochastic Multi-Objective Optimization via Hashing and Randomization
par: Li, Jinzhao, et autres
Publié: (2026)

Transfer Learning from Foundational Optimization Embeddings to Unsupervised SAT Representations
par: Pal, Koyena, et autres
Publié: (2026)

Can Transformers Learn to Verify During Backtracking Search?
par: Phua, Yin Jun, et autres
Publié: (2026)

ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
par: Sharifi, Iman, et autres
Publié: (2026)

What are the Right Symmetries for Formal Theorem Proving?
par: Olejniczak, Krzysztof, et autres
Publié: (2026)

Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
par: Boetius, David, et autres
Publié: (2026)

Learning to Solve and Optimize by Evolving Code
par: Semmelrock, Veronika, et autres
Publié: (2026)

Towards Understanding the Expressive Power of GNNs with Global Readout
par: Funk, Maurice, et autres
Publié: (2026)

Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)
par: Olivieri, Pierriccardo, et autres
Publié: (2026)

On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks
par: Damera, Sai Sandeep, et autres
Publié: (2026)