# Cross-Source Reasoning-based Correction for Author Name Disambiguation

arXiv: https://arxiv.org/abs/2606.08617 · HTML: https://mlsanity.com/paper/2606.08617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer](https://mlsanity.com/paper/2010.03158/) (2020)
- [Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance](https://mlsanity.com/paper/2311.01108/) (2023)
- [Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking](https://mlsanity.com/paper/2002.01854/) (2020)
- [OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services](https://mlsanity.com/paper/2103.02410/) (2021)
- [OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining](https://mlsanity.com/paper/2402.15810/) (2024)
- [Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance](https://mlsanity.com/paper/2504.02901/) (2025)
- [Name Disambiguation in Anonymized Graphs using Network Embedding](https://mlsanity.com/paper/1702.02287/) (2017)
- [Author Name Disambiguation on Heterogeneous Information Network with Adversarial Representation Learning](https://mlsanity.com/paper/2002.09803/) (2020)
- [Web-Scale Academic Name Disambiguation: the WhoIsWho Benchmark, Leaderboard, and Toolkit](https://mlsanity.com/paper/2302.11848/) (2023)
- [GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Model](https://mlsanity.com/paper/2412.03930/) (2024)
- [Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement](https://mlsanity.com/paper/2505.19675/) (2025)
- [BOND: Bootstrapping From-Scratch Name Disambiguation with Multi-task Promoting](https://mlsanity.com/paper/2404.08322/) (2024)

## Abstract (arXiv)

Author name disambiguation is a critical challenge in academic search systems, often addressed through from-scratch and real-time disambiguation approaches. However, current algorithms remain vulnerable to cumulative errors of paper-author assignments and overlook inconsistent assignments across different sources. Resorting to expert annotation is resource-intensive. To this end, this paper explores a new perspective for author name disambiguation: cross-source correction by leveraging inconsistent assignments across sources. We propose CrossND, a full-stack framework that integrates data refinement, cross-source reasoning, and test-time scaling. First, a chain-of-refinement pipeline denoises author profiles and produces more accurate paper-author matching probabilities. Second, a supervised fine-tuning process incorporates these refined signals and a probabilistic soft logic-based cross-correction module to infer the assignments of which sources are incorrect. Third, test-time scaling further enhances the accuracy and robustness of the predictions. Experiments on real-world datasets indicate that CrossND consistently outperforms 17 baselines by leveraging cross-source reasoning without human intervention.