# Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution

arXiv: https://arxiv.org/abs/2605.25814 · HTML: https://mlsanity.com/paper/2605.25814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 72 references that are in the map.
- First posted on arXiv 25 May 2026.

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

- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Large Language Models as Data Preprocessors](https://mlsanity.com/paper/2308.16361/) (2023)
- [ZeroER: Entity Resolution using Zero Labeled Examples](https://mlsanity.com/paper/1908.06049/) (2019)
- [A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching](https://mlsanity.com/paper/2003.13114/) (2020)
- [ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries](https://mlsanity.com/paper/2501.04901/) (2025)
- [Leveraging Transitive Relations for Crowdsourced Joins](https://mlsanity.com/paper/1408.6916/) (2014)
- [Flexible Models for Microclustering with Application to Entity Resolution](https://mlsanity.com/paper/1610.09780/) (2016)
- [In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration](https://mlsanity.com/paper/2506.02509/) (2025)
- [Ground Truth Inference for Weakly Supervised Entity Matching](https://mlsanity.com/paper/2211.06975/) (2022)
- [On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach](https://mlsanity.com/paper/2401.03426/) (2024)
- [Select Your Questions Wisely: For Entity Resolution With Crowd Errors](https://mlsanity.com/paper/1701.08288/) (2017)

## Abstract (arXiv)

Dirty entity resolution (ER), which identifies records referring to the same real-world entity from a single, messy dataset, is a fundamental task in data management and mining. However, the dominant blocking-matching-clustering paradigm for ER suffers from critical flaws. Its cascaded, decoupled workflow essentially produces a static, sparse graph plagued by missing edges (due to blocking failures) and noisy links (due to matching errors), causing error propagation and yielding suboptimal clusters, particularly when rigid transitivity is imposed in the clustering. We contend that matching and clustering are fundamentally synergistic, both optimizing for the construction of an ideal entity graph. Building upon this insight, we propose Alper, a unified framework that integrates these steps into an iterative probabilistic label propagation process over a global, evolving graph. Unlike disjoint blocking, Alper refines the graph structure and labels dynamically by adaptively integrating "weak but cheap" signals from graph propagation with "strong but expensive" LLM-based pairwise queries. For higher cost-effectiveness, we formulate the signal selection as a constrained optimization problem maximizing cumulative marginal gain under a query budget, solved via our greedy algorithm with provable theoretical guarantees. Our extensive experiments over eight benchmark datasets demonstrate that Alper is consistently superior to state-of-the-art cascaded pipelines.