Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
📰 ArXiv cs.AI
arXiv:2604.19000v1 Announce Type: cross Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mathematical statements. In this work, we introduce D
Full Article
Title: Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
Abstract:
arXiv:2604.19000v1 Announce Type: cross Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mathematical statements. In this work, we introduce D
Abstract:
arXiv:2604.19000v1 Announce Type: cross Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mathematical statements. In this work, we introduce D
DeepCamp AI