# Constraint-Guided Enterprise Data Mapping with Large Language Models

arXiv: https://arxiv.org/abs/2608.24218 · HTML: https://mlsanity.com/paper/2608.24218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [CRANE: Reasoning with constrained LLM generation](https://mlsanity.com/paper/2502.09061/) (2025)
- [Valentine: Evaluating Matching Techniques for Dataset Discovery](https://mlsanity.com/paper/2010.07386/) (2020)
- [Entity Matching using Large Language Models](https://mlsanity.com/paper/2310.11244/) (2023)
- [CleanAgent: Automating Data Standardization with LLM-based Agents](https://mlsanity.com/paper/2403.08291/) (2024)
- [ReMatch: Retrieval Enhanced Schema Matching with LLMs](https://mlsanity.com/paper/2403.01567/) (2024)
- [NameGuess: Column Name Expansion for Tabular Data](https://mlsanity.com/paper/2310.13196/) (2023)
- [Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching](https://mlsanity.com/paper/2501.08686/) (2025)
- [Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving](https://mlsanity.com/paper/2512.23511/) (2025)
- [GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics](https://mlsanity.com/paper/2503.21735/) (2025)
- [Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration](https://mlsanity.com/paper/2511.20285/) (2025)

## Abstract (arXiv)

Enterprise entity alignment must handle semi-structured records, implicit attributes, and unit or granularity mismatches. Manual matching is still common in practice, but does not scale as schemas and providers evolve. LLM-only matching improves semantic recall, yet can violate structural and physical invariants, producing fluent yet operationally invalid correspondences. We propose constraint-guided mapping (CGM), a neuro-symbolic method with three stages: (i) schema-grounded admissibility constraints with metadata mc = <tau_c, delta_c>, where tau_c denotes the constraint type and delta_c provides executable relation and normalization logic; (ii) constraint-restricted candidate generation with cascade relaxation to guarantee a nonempty feasible set under noise; and (iii) neural ranking with bounded LLM disambiguation restricted to that feasible set. Methodologically, constraints operate as hypothesis-space operators rather than post-hoc validators, enabling controlled degradation under relaxation and auditable, human-guidable decisions. On a controlled structural-decoy benchmark, hard admissibility shrinks the candidate space by ~480x without dropping the GT, and a layer-by-layer ablation shows this gate, not the LLM, is the decisive lift (F1 0.08 to 0.66). The benefit is model-independent and adds no extra inference cost: a small model with constraints matches a frontier LLM used without them at ~28x lower cost. The method, not a single tuned configuration, transfers across seven enterprise makes (macro F1 0.70), each under its own automatically discovered, expert-refinable constraints, and lowers expert effort by ~7x versus spreadsheet workflows. Public Valentine results add an external ranking sanity check and mark the boundary: constraints should be hard only where structural invariants are match-determining.