arXiv cs.AI· Haobo Li, Wenshuo Zhang, Wenxiao Zhao, Eunseo Jung, Rui Sheng, Yushi Sun, Peiqin Zhuang, Hao Chen, Fenghua Ling·· 9 天前AI 评分23
RISR：用残差信息引导大语言模型发现科学方程
RISR: Residual-Informed Scientific Equation Discovery with Large Language Models
AI 导读
RISR 是一种残差信息驱动的符号回归方法，通过残差编码器将输入、目标、当前预测与残差压缩为连续 token 来条件化语言模型生成公式，并用双视角关系编码器预测候选修正的拟合后效用。
正文 · 原文
Abstract:Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a residual-informed method that uses these error patterns to guide formula discovery and learn which corrections are worth fitting. A residual encoder compresses aligned inputs, targets, current predictions, and residuals into continuous tokens that condition a language model to propose formulas. For subsequent refinement, a dual-view relational encoder uses additive and regularized multiplicative residuals to predict the post-fit utility of candidate corrections. We evaluate RISR on scientific tasks from the LLM-SRBench. RISR achieves 63.57% and 38.50% ID accuracy at the 1% and 0.1% pointwise relative-error tolerances, respectively. The corresponding OOD accuracies are 56.07% and 38.24%. RISR outperforms the reported baselines using the same backbone. The results show that our residual-informed approach can improve numerical equation recovery.
| Subjects: | Symbolic Computation (cs.SC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11387 [cs.SC] |
| (or arXiv:2610.11387v1 [cs.SC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11387 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haobo Li [view email]
[v1]
Thu, 8 Oct 2026 07:17:41 UTC (1,671 KB)
来源：arXiv cs.AI · arxiv.org