NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
Not on the map. Why?
Abstract (arXiv)
Although the Gradient Boosted Decision Trees (GBDTs) dominate industrial tabular applications, upgrading legacy models in high-concurrency production environments still faces prohibitive retraining costs and systemic risks. To address this problem, we present NSR-Boost, a neuro-symbolic residual boosting framework designed specifically for industrial scenarios. Its core advantage lies in being ``non-intrusive''. It treats the legacy model as a frozen model and performs targeted repairs on "hard regions" where predictions fail. The framework comprises three key stages: First, finding hard regions through residuals, then generating interpretable experts by generating symbolic code structures using Large Language Model (LLM) and fine-tuning parameters using Bayesian optimization, and finally dynamically integrating experts with legacy model output through a lightweight aggregator. Experimental results demonstrate that the framework significantly outperforms state-of-the-art (SOTA) baselines across six public datasets and one private dataset. More importantly, we report the successful deployment of NSR-Boost within the core financial risk control system of Qfin Holdings, where empirical results on real-world online traffic exhibit superior performance improvements and a significant reduction in the bad rate. In conclusion, it effectively captures long-tail risks missed by traditional models and offers a safe, low-cost evolutionary paradigm for industry.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 39 references that are in the map. First posted on arXiv 15 Jan 2026.
Builds on
16 of 39 references.
References · 16
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2021Revisiting Deep Learning Models for Tabular Datacited by 740
- 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
- 2021Tabular Data: Deep Learning is Not All You Needcited by 535
- 2014OpenML: networked science in machine learningcited by 526
- 2023Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineeringcited by 127
- 2025NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Modelcited by 108
- 2024Symbolic Regression with a Learned Concept Librarycited by 83
- 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 81
- 2019The autofeat Python Library for Automated Feature Engineering and Selectioncited by 73
- 2019OpenML-Python: an extensible Python API for OpenMLcited by 63
4 more
- 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoningcited by 49
- 2025LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizerscited by 38
- 2025DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experiencecited by 22
- 2025LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regressioncited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.