arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.23959cs.CLcs.LG
收藏

我的嵌入是否反映了 $A = B$?评估嵌入模型中的数学等价性

Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models

University of Washington(华盛顿大学);Axiom Math;Pacific Northwest National Laboratory(太平洋西北国家实验室)

Jiaying Ye, Samarth Rao, Leo Carlin, Kedar Chintalapati, Saharsh Bhargava, Rachit Jaiswal, Michael Zhou, Jared Darlington, Jiahe Lu, Jarod Alper, Vasily Ilin, Henry Kvinge

AI总结:

针对当前嵌入模型无法识别数学等价陈述的问题,提出MELD数据集和对比学习方法,使嵌入能对齐不同形式化的数学表述。

摘要:

由于数学高度抽象,一个陈述根据其所属的子领域可能呈现非常不同的形式。许多突破发生在研究人员发现某个问题已在不同领域得到解答之后。同时,与形式化相关的新资源的增长,增加了对能够在数学‘语言’(例如,从Lean到自然语言)之间进行高效可靠导航的工具的需求。在本文中,我们研究当前嵌入模型是否捕捉数学等价性。为此,我们引入了数学等价但词汇不同对(MELD)数据集,这是一个用非常不同的语言表达的数学等价陈述的集合。我们表明,当前最先进的嵌入模型倾向于根据用于表述的术语而不是底层数学来对陈述进行分组。受此启发,我们提出了一种对比学习方法,用于学习数学文本的嵌入,重点是将非正式陈述与不同的形式化对齐。我们的实验表明,这不仅在非正式-形式检索任务上带来了改进,而且在仅包含自然语言陈述的MELD上也带来了改进。

英文摘要:

Because mathematics is highly abstract, a single statement can take very different forms depending on what subfield it is framed in. There are many examples where breakthroughs occurred after researchers discovered that a question had already been answered in a different field. At the same time, the growth of new resources related to formalization has increased the need for tools that enable efficient and reliable navigation between mathematical 'languages' (e.g., from Lean to natural language). In this paper, we investigate whether current embedding models capture mathematical equivalence. To do this, we introduce the Mathematically Equivalent but Lexically Different Pairs (MELD) Dataset, a collection of mathematically equivalent statements that are expressed in very different language. We show that current state-of-the-art embedding models tend to group statements by the terminology used to make them instead of the underlying math. Motivated by this, we propose a contrastive approach to learning embeddings of mathematical text that focuses on aligning informal statements with different formalizations. Our experiments demonstrate that this leads to improvements not only on informal-formal retrieval tasks but also on MELD, which only contains natural language statements.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑