Oct 2025· arXiv.org· Vol abs/2510.11944· 0 citations· 47 references
Computer Science
TL;DR
TopoAlign is proposed, a framework that unlocks widely available code repositories as training resources for Math LLMs and decomposes code into docstrings, main functions, and dependency functions, and reassembles these components into analogues that structurally mirror formal statements.
Abstract
Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Yet, the performance of current Math LLMs is constrained by the scarcity of large-scale corpora, particularly those containing pairs of informal and formal statements. Interestingly, the formal languages used in autoformalisation share structural similarities with programming languages, and code data is available at scale. However, current models trained on code do not transfer effectively to formal math, due to structural and syntactic differences between them. To address this, we propose TopoAlign, a framework that unlocks widely available code repositories as training resources for Math LLMs. TopoAlign decomposes code into docstrings, main functions, and dependency functions, and reassembles these components into analogues that structurally mirror formal statements. We train three state-of-the-art models, DeepSeek-Math, Qwen-3 and Herald, and evaluate them on the MiniF2F, Putnam, and ProofNet benchmarks. TopoAlign provides substantial gains for DeepSeek-Math, improving performance by 17.77% on BEq@10 and 68.82% on typecheck@10, and also measurably improves Herald by 0.12% on BEq@10 and 1.09% on typecheck@10 despite introducing no new mathematical knowledge.
MathForm is introduced, an autoformalization framework for constructing verified training data through Mathlib knowledge retrieval and verification-guided iterative refinement, and outperforming multiple specialized 32B autoformalizers.
Lushi Pu, Weiming Zhang, Xinheng Xie et al.· 0 citations
Compilable Academic Document Parsing (CADP) is proposed, a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page.
GraphAlignCoder is introduced, a training framework that transfers explicit correctness structure into code generation and consistently outperforms the base model, code-only SFT, and CodeRL across all benchmarks.
Yue-Ke Zhang, Zihan Fang, Kevin Leach et al.· 0 citations
Two language-model-based strategies are proposed for semantic code document segmentation, including a line-by-line approach that classifies each line of code separately before grouping the results into functional units, and a range-based approach that aims to directly determine groups of code lines from the input.
A. Dahou, A. Scherp, Sebastian Kurten et al.· Proceedings of the 2026 ACM...· 0 citations
Two novel contributions are introduced: CodeEval and CodeQual, an open-source execution framework that provides researchers with a ready-to-use evaluation pipeline for evaluating and improving LLMs in software engineering contexts, encompassing both functional correctness assessment and subjective code quality evaluati...
Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a given context using faithful deductive processes. However, LLM reasoning has often been shown to be sensitive to small surface-level variations in problem formulation, ra...
Ramya Keerthy Thatikonda, W. Buntine, Ehsan Shareghi· 0 citations