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

arXiv: https://arxiv.org/abs/2512.07246 · HTML: https://mlsanity.com/paper/2512.07246/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations](https://mlsanity.com/paper/2504.14150/) (2025)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching](https://mlsanity.com/paper/2405.16884/) (2024)
- [HoloDetect: Few-Shot Learning for Error Detection](https://mlsanity.com/paper/1904.02285/) (2019)
- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [Schema Matching with Large Language Models: an Experimental Study](https://mlsanity.com/paper/2407.11852/) (2024)
- [Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets](https://mlsanity.com/paper/2503.06664/) (2025)
- [GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees](https://mlsanity.com/paper/2411.08257/) (2024)
- [On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing](https://mlsanity.com/paper/2501.02191/) (2025)
- [The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators](https://mlsanity.com/paper/2407.11004/) (2024)
- [Few-shot LLM Synthetic Data with Distribution Matching](https://mlsanity.com/paper/2502.08661/) (2025)
- ["Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models](https://mlsanity.com/paper/2409.18594/) (2024)
- [CORTEX: A Cost-Sensitive Rule and Tree Extraction Method](https://mlsanity.com/paper/2502.03200/) (2025)
- [RCScore: Quantifying Response Consistency in Large Language Models](https://mlsanity.com/paper/2510.26193/) (2025)

## Built on by (most cited first, 2 of 2)

- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization](https://mlsanity.com/paper/2607.25228/) (2026)

## Abstract (arXiv)

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 of large language models (LLMs) to directly label whether a cell is erroneous. However, this LLM-as-a-labeler pipeline produces predictions through an implicit black-box process with limited traceability and explicit justification, and relies on stochastic single-pass inference, resulting in inconsistent and insufficiently robust detections across contexts. To address these limitations, we propose an LLM-as-an-inducer framework that uses an LLM to induce a decision tree for ED, termed TreeED, and ensembles multiple such trees for consensus detection, termed ForestED. Based on prompts derived from data context, decision tree specifications, and output requirements, TreeED queries the LLM to induce a decision tree skeleton whose root-to-leaf paths specify the stepwise procedure for evaluating a sample. Each tree contains three types of nodes: (1) rule nodes that perform simple validation checks, such as format or range constraints; (2) Graph Neural Network (GNN) nodes that capture complex patterns, such as functional dependencies; and (3) leaf nodes that output the final decision as error or clean. ForestED employs uncertainty sampling to obtain multiple informative row subsets and constructs a decision tree for each subset using TreeED. It then applies an Expectation-Maximization-based algorithm to jointly estimate tree reliability and optimize the consensus ED prediction. Experiments demonstrate that our methods are accurate, explainable, and robust, achieving an average F1-score improvement of 16.1% over the best baseline.