paper-with-me

Papers

FormalAlign: Automated Alignment Evaluation for Autoformalization

2024-10-14 · Jianqiao Lu, Yingjia Wan, Yinya Huang, Jing Xiong, Zhengying Liu, Zhijiang Guo

Autoformalization aims to convert informal mathematical proofs into machine-verifiable formats, bridging the gap between natural and formal languages. However, ensuring semantic alignment between the informal and formalized statements remains challenging. Existing approaches heavily rely on manual verification, hindering scalability. To address this, we introduce \textsc{FormalAlign}, the first automated framework designed for evaluating the alignment between natural and formal languages in autoformalization. \textsc{FormalAlign} trains on both the autoformalization sequence generation task and the representational alignment between input and output, employing a dual loss that combines a pair of mutually enhancing autoformalization and alignment tasks. Evaluated across four benchmarks augmented by our proposed misalignment strategies, \textsc{FormalAlign} demonstrates superior performance. In our experiments, \textsc{FormalAlign} outperforms GPT-4, achieving an Alignment-Selection Score 11.58\% higher on \forml-Basic (99.21\% vs. 88.91\%) and 3.19\% higher on MiniF2F-Valid (66.39\% vs. 64.34\%). This effective alignment evaluation significantly reduces the need for manual verification. Both the dataset and code can be accessed via~\url{https://github.com/rookie-joe/FormalAlign}.

📄 PDF Abstract BibTeX arXiv:2410.10135

Code (1)

rookie-joe/formalalign 공식 구현

Tasks

Mathematical Proofsvalid

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

FormalRx: Rectify and eXamine Semantic Failures in Autoformalization

2026-07-06 · Haocheng Wang, Baiyu Huang, Yingjia Wan, Xiao Zhu 외 arxiv

The veracious semantic alignment in autoformalization is significant for formal mathematical reasoning. However, existing evaluations provide only opaque binary verdicts or scalar scores, offering no interpretable insigh…

Mathematical Reasoning

Generalized Tree Edit Distance (GTED): A Faithful Evaluation Metric for Statement Autoformalization

2025-07-10 · Yuntian Liu, Tao Zhu, Xiaoyang Liu, Yu Chen 외 arxiv

Statement autoformalization, the automated translation of statements from natural language into formal languages, has become a subject of extensive research, yet the development of robust automated evaluation metrics rem…

Automated Theorem ProvingSemantic Similarity

Autoformalization in the Era of Large Language Models: A Survey

2025-05-29 · Ke Weng, Lun Du, Sirui Li, Wangyue Lu 외

Autoformalization, the process of transforming informal mathematical propositions into verifiable formal representations, is a foundational task in automated theorem proving, offering a new perspective on the use of math…

Automated Theorem Proving

Quantifying the Importance of Data Alignment in Downstream Model Performance

2025-01-14 · Krrish Chawla, Aryan Sahai, Mario DePavia, Sudharsan Sundar 외

Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Ve…

Machine Translation

RLMEval: Evaluating Research-Level Neural Theorem Proving

2025-10-29 · Auguste Poiroux, Antoine Bosselut, Viktor Kunčak arxiv

Despite impressive results on curated benchmarks, the practical impact of large language models (LLMs) on research-level neural theorem proving and proof autoformalization is still limited. We introduce RLMEval, an evalu…