Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ying, Wangyang, Bai, Haoyue, Gong, Nanxu, Wang, Xinyuan, Dong, Sixun, Chen, Haifeng, Fu, Yanjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913851023294464
author Ying, Wangyang
Bai, Haoyue
Gong, Nanxu
Wang, Xinyuan
Dong, Sixun
Chen, Haifeng
Fu, Yanjie
author_facet Ying, Wangyang
Bai, Haoyue
Gong, Nanxu
Wang, Xinyuan
Dong, Sixun
Chen, Haifeng
Fu, Yanjie
contents The data-to-equation (Data2Eqn) task aims to discover interpretable mathematical equations that map observed values to labels, offering physical insights and broad applicability across academic and industrial domains. Genetic programming and traditional deep learning-based approaches suffer from search inefficiency and poor generalization on small task-specific datasets. Foundation models showed promise in this area, but existing approaches suffer from: 1) They are pretrained on general-purpose data distributions, making them less effective for domain-specific tasks; and 2) their training objectives focus on token-level alignment, overlooking mathematical semantics, which can lead to inaccurate equations. To address these issues, we aim to enhance the domain adaptability of foundation models for Data2Eqn tasks. In this work, we propose a reinforcement learning-based finetuning framework that directly optimizes the generation policy of a pretrained model through reward signals derived from downstream numerical fitness. Our method allows the model to adapt to specific and complex data distributions and generate mathematically meaningful equations. Extensive experiments demonstrate that our approach improves both the accuracy and robustness of equation generation under complex distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
Ying, Wangyang
Bai, Haoyue
Gong, Nanxu
Wang, Xinyuan
Dong, Sixun
Chen, Haifeng
Fu, Yanjie
Machine Learning
Artificial Intelligence
The data-to-equation (Data2Eqn) task aims to discover interpretable mathematical equations that map observed values to labels, offering physical insights and broad applicability across academic and industrial domains. Genetic programming and traditional deep learning-based approaches suffer from search inefficiency and poor generalization on small task-specific datasets. Foundation models showed promise in this area, but existing approaches suffer from: 1) They are pretrained on general-purpose data distributions, making them less effective for domain-specific tasks; and 2) their training objectives focus on token-level alignment, overlooking mathematical semantics, which can lead to inaccurate equations. To address these issues, we aim to enhance the domain adaptability of foundation models for Data2Eqn tasks. In this work, we propose a reinforcement learning-based finetuning framework that directly optimizes the generation policy of a pretrained model through reward signals derived from downstream numerical fitness. Our method allows the model to adapt to specific and complex data distributions and generate mathematically meaningful equations. Extensive experiments demonstrate that our approach improves both the accuracy and robustness of equation generation under complex distributions.
title Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.15572