Imagen de Portada

CuDIP: Enhancing Theorem Proving in LLMs via Curriculum Learning-based Direct Preference Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Shuming, Zuo, Ruobing, He, Gaolei, Wang, Jianlin, Xu, Chenyang, Yang, Zhengfeng
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
por: Zuo, Ruobing, et al.
Publicado: (2026)

A Combinatorial Identities Benchmark for Theorem Proving via Automated Theorem Generation
por: Xiong, Beibei, et al.
Publicado: (2025)

A Context-Enhanced Framework for Sequential Graph Reasoning
por: Shi, Shuo, et al.
Publicado: (2024)

Steering LLMs for Formal Theorem Proving
por: Kirtania, Shashank, et al.
Publicado: (2025)

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
por: Cao, Chuxue, et al.
Publicado: (2025)

On Reasoning-Centric LLM-based Automated Theorem Proving
por: Sun, Yican, et al.
Publicado: (2026)

Learning to Reason with Insight for Informal Theorem Proving
por: Li, Yunhe, et al.
Publicado: (2026)

Proving Theorems Recursively
por: Wang, Haiming, et al.
Publicado: (2024)

Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
por: Wen, Xin-Cheng, et al.
Publicado: (2025)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
por: Fu, Yuhan, et al.
Publicado: (2024)

A Survey on Deep Learning for Theorem Proving
por: Li, Zhaoyu, et al.
Publicado: (2024)

SubgoalXL: Subgoal-based Expert Learning for Theorem Proving
por: Zhao, Xueliang, et al.
Publicado: (2024)

Curriculum Direct Preference Optimization for Diffusion and Consistency Models
por: Croitoru, Florinel-Alin, et al.
Publicado: (2024)

Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically
por: Dong, Kefan, et al.
Publicado: (2024)

BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
por: Petrov, Ivo, et al.
Publicado: (2025)

Sponsored Search Auction Design Beyond Single Utility Maximization
por: Xu, Changfeng, et al.
Publicado: (2024)

Direct Preference Optimization for LLM-Enhanced Recommendation Systems
por: Sun, Chao, et al.
Publicado: (2024)

LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation
por: Lai, Junyu, et al.
Publicado: (2025)

De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning
por: Hou, Junyu
Publicado: (2025)

Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
por: Zhao, Mengjie, et al.
Publicado: (2026)

Twitch: Learning Abstractions for Equational Theorem Proving
por: Axelrod, Guy, et al.
Publicado: (2026)

Partial Label Learning for Automated Theorem Proving
por: Zombori, Zsolt, et al.
Publicado: (2025)

An In-Context Learning Agent for Formal Theorem-Proving
por: Thakur, Amitayush, et al.
Publicado: (2023)

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
por: Zhang, Ziyin, et al.
Publicado: (2025)

Aligning CodeLLMs with Direct Preference Optimization
por: Miao, Yibo, et al.
Publicado: (2024)

Automated Formal Proofs of Combinatorial Identities via Wilf-Zeilberger Guidance and LLMs
por: Xiong, Beibei, et al.
Publicado: (2026)

Open-Book Neural Algorithmic Reasoning
por: Li, Hefei, et al.
Publicado: (2024)

Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning
por: Ji, Xingguang, et al.
Publicado: (2025)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
por: Zhang, Xuemiao, et al.
Publicado: (2025)

2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization
por: Li, Mengyang, et al.
Publicado: (2025)

Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
por: Xu, Shuo, et al.
Publicado: (2026)

Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
por: Yang, Sen, et al.
Publicado: (2024)

LeanAgent: Lifelong Learning for Formal Theorem Proving
por: Kumarappan, Adarsh, et al.
Publicado: (2024)

Psychometric-Based Evaluation for Theorem Proving with Large Language Models
por: Zhang, Jianyu, et al.
Publicado: (2025)

Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions
por: Yang, Xiao, et al.
Publicado: (2024)

OProver: A Unified Framework for Agentic Formal Theorem Proving
por: Ma, David, et al.
Publicado: (2026)

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
por: Croitoru, Florinel-Alin, et al.
Publicado: (2026)

Benchmarking Testing in Automated Theorem Proving
por: Kim, Jongyoon, et al.
Publicado: (2026)

Automated Theorem Proving for Prolog Verification
por: Mesnard, Fred, et al.
Publicado: (2026)

Canonical for Automated Theorem Proving in Lean
por: Norman, Chase, et al.
Publicado: (2025)