# Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization

arXiv: https://arxiv.org/abs/2607.25228 · HTML: https://mlsanity.com/paper/2607.25228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 28 Jul 2026.

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [A cost function for similarity-based hierarchical clustering](https://mlsanity.com/paper/1510.05043/) (2015)
- [KGGen: Extracting Knowledge Graphs from Plain Text with Language Models](https://mlsanity.com/paper/2502.09956/) (2025)
- [GitTables: A Large-Scale Corpus of Relational Tables](https://mlsanity.com/paper/2106.07258/) (2021)
- [MiniMax Sparse Attention](https://mlsanity.com/paper/2606.13392/) (2026)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements](https://mlsanity.com/paper/2505.22959/) (2025)
- [PrivGemo: Privacy-Preserving Dual-Tower Graph Retrieval for Empowering LLM Reasoning with Memory Augmentation](https://mlsanity.com/paper/2601.08739/) (2026)
- [Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory](https://mlsanity.com/paper/2603.15280/) (2026)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations](https://mlsanity.com/paper/2508.17203/) (2025)
- [Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection](https://mlsanity.com/paper/2512.07246/) (2025)
- [HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery](https://mlsanity.com/paper/2601.01015/) (2026)
- [TabEmb: Joint Semantic-Structure Embedding for Table Annotation](https://mlsanity.com/paper/2604.18939/) (2026)
- [Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking](https://mlsanity.com/paper/2604.20283/) (2026)
- [Collaborative Large and Small Language Models for Accurate and Scalable Data Repair](https://mlsanity.com/paper/2606.17582/) (2026)

## Abstract (arXiv)

Column annotation (CA), including column type annotation (CTA) and column property annotation (CPA), aims to identify the meanings of table columns and the semantic relationships among them. Recent CA methods usually use various neural models to learn column representations and directly map them to label categories, thereby (1) sacrificing model interpretability and adaptivity, and (2) overlooking rich label semantics and ultimately limiting accuracy. To address these limitations, we propose SymCA, an LLM-empowered interpretable CA framework that materializes column annotation as a global-to-local symbolic decision process. SymCA consists of two components: (1) global skeleton induction, which constructs a semantic skeleton over the label space, and (2) local substrate evolution, which evolves predictive substrates within the skeleton. Specifically, to exploit label semantics while preserving an interpretable decision process, the global skeleton induction module leverages LLMs to generate candidate hypernym-inspired tree-structured semantic skeletons and employs a Minimum Bayes Risk (MBR)-based consensus strategy to select a robust skeleton against generation variance. Since different internal nodes require different evidence to distinguish among their child nodes, the local substrate evolution module materializes each internal node as an executable and evolvable predictive substrate. Over multiple evolution rounds, each substrate trains an interpretable random forest classifier with the current operator set, leverages the LLM to propose node-specific operator modifications, and uses an exploration-exploitation strategy to prioritize promising substrates. Extensive experiments demonstrate that SymCA is accurate, robust, and interpretable, outperforming the strongest baselines by an average of 6.42% in Micro-F1 and 11.03% in Macro-F1.