Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection

2025-12-08

AI Summary

Existing LLM-based error detection methods suffer from poor interpretability and insufficient robustness due to prompt sensitivity. To address these challenges, we propose the “LLM as Inducer” framework, which leverages large language models to induce hybrid-structured decision trees—comprising rule-based nodes, GNN-based nodes, and leaf nodes—specifically for tabular error detection. The framework employs uncertainty-aware sampling and the EM algorithm to ensemble multiple such trees, yielding consensus predictions grounded in reliability estimation. This work is the first to employ LLMs for end-to-end decision tree architecture construction, simultaneously ensuring logical interpretability and output stability. Experiments across multiple benchmark datasets demonstrate an average 16.1% improvement in F1-score over state-of-the-art baselines, confirming superior accuracy, strong interpretability, and enhanced robustness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Reasoning under Uncertainty: Uncertainty Representations
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data, is important for ensuring data quality. Recent state-of-the-art ED methods leverage the pre-trained knowledge and semantic capability embedded in large language models (LLMs) to directly label whether a cell is erroneous. However, this LLM-as-a-labeler pipeline (1) relies on the black box, implicit decision process, thus failing to provide explainability for the detection results, and (2) is highly sensitive to prompts, yielding inconsistent outputs due to inherent model stochasticity, therefore lacking robustness. To address these limitations, we propose an LLM-as-an-inducer framework that adopts LLM to induce the decision tree for ED (termed TreeED) and further ensembles multiple such trees for consensus detection (termed ForestED), thereby improving explainability and robustness. Specifically, based on prompts derived from data context, decision tree specifications and output requirements, TreeED queries the LLM to induce the decision tree skeleton, whose root-to-leaf decision paths specify the stepwise procedure for evaluating a given sample. Each tree contains three types of nodes: (1) rule nodes that perform simple validation checks (e.g., format or range), (2) Graph Neural Network (GNN) nodes that capture complex patterns (e.g., functional dependencies), and (3) leaf nodes that output the final decision types (error or clean). Furthermore, ForestED employs uncertainty-based sampling to obtain multiple row subsets, constructing a decision tree for each subset using TreeED. It then leverages an Expectation-Maximization-based algorithm that jointly estimates tree reliability and optimizes the consensus ED prediction. Extensive xperiments demonstrate that our methods are accurate, explainable and robust, achieving an average F1-score improvement of 16.1% over the best baseline.

Problem

• Improves explainability of error detection in tabular data
• Enhances robustness against prompt sensitivity in LLMs
• Ensembles decision trees for consensus-based error identification

Innovation

• LLM induces decision trees for explainable error detection
• Hybrid tree nodes combine rule checks and GNN pattern capture
• Ensemble trees with EM algorithm boost robustness and consensus