Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts

• URL: http://arxiv.org/abs/2605.23597v1
• Date: Fri, 22 May 2026 13:06:03 GMT
• Title: Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
• Abstract summary: This paper introduces Structure-Guided Entity Resolution (SGER), a novel framework that fine-tunes an Large Language Model through a two-phase curriculum.<n>We evaluate SGER in the challenging context of Indian identity data, one of the most linguistically diverse and noisy environments globally.<n>SGER achieves 99.02% accuracy and an F1 of 0.994 on a held-out set of 50,000 real-world pairs, outperforming GPT-4o few-shot prompting and single-stage fine-tuning baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Matching person names across heterogeneous records is a core challenge in entity resolution, especially within linguistically and culturally complex environments. Variations in naming conventions, inconsistent transliteration across scripts, and frequent data entry errors make it difficult to unify user identities, an essential requirement for Know Your Customer (KYC) compliance. While Large Language Models have shown promise in understanding natural language, they often struggle with the structured ambiguity present in such domain-specific settings. This paper introduces Structure-Guided Entity Resolution (SGER), a novel framework that fine-tunes an LLM through a two-phase curriculum. The model is first trained to parse the grammatical and semantic structure of personal names, then optimized for the downstream task of binary entity matching. We evaluate SGER in the challenging context of Indian identity data, one of the most linguistically diverse and noisy environments globally. SGER achieves 99.02% accuracy and an F1 of 0.994 on a held-out set of 50,000 real-world pairs, outperforming GPT-4o few-shot prompting and single-stage fine-tuning baselines. The system is fully deployed in production at Dream11, the world's largest fantasy sports platform, serving 250M+ users. Our results demonstrate that curriculum-guided training enables robust, high-precision entity resolution in real-world multilingual systems at scale.

Related papers

• A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models [0.0]
  We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition.<n>Inspired by the Declarative-Procedural framework, we analyze lexical, grammatical, and syntactic processing in a decoder-only English-German MoE Transformer trained under sequential language exposure.
  arXiv  Detail & Related papers  (2026-08-15T07:53:12Z)
• Multilingual Refusal Alignment for Safer Large Language Models [53.64286756804503]
  We investigate whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities.<n>We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models.<n>Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
  arXiv  Detail & Related papers  (2026-04-24T09:29:14Z)
• FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition [12.125413756152833]
  We introduce FiNERweb, a dataset-creation pipeline that scales the teacher-student paradigm to 91 languages and 25 scripts.<n>Building on FineWeb-Edu, our approach trains regression models to identify NER-relevant passages and annotate them with multilingual LLMs.<n>Our experiments show that the regression model achieves more than 84 F1, and that models trained on FiNERweb obtain comparable or improved performance in zero shot transfer settings.
  arXiv  Detail & Related papers  (2025-12-15T20:36:39Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• Fine-Tuned Language Models for Domain-Specific Summarization and Tagging [3.543800643014229]
  This paper presents a pipeline integrating fine-tuned large language models (LLMs) with named entity recognition (NER) for efficient domain-specific text summarization and tagging.<n>The authors address the challenge posed by rapidly evolving sub-cultural languages and slang, which complicate automated information extraction and law enforcement monitoring.
  arXiv  Detail & Related papers  (2025-10-29T12:33:48Z)
• Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition [9.044039469025009]
  We propose a novel Generative Sign-description Prompts Multi-positive Contrastive learning (GSP-MC) method to produce precise multipart descriptions.<n>The GSP-MC method also employs a dual-encoder architecture to bidirectionally align hierarchical skeleton features with multiple text descriptions.<n> Experiments demonstrate state-of-the-art performance against existing methods on the Chinese SLR500 (reaching 97.1%) and Turkish AUTSL datasets (97.07% accuracy)
  arXiv  Detail & Related papers  (2025-05-05T00:57:57Z)
• Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
  Large language models (LLMs) can understand human instructions, but struggle with complex instructions. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions. We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
  arXiv  Detail & Related papers  (2023-09-17T04:18:39Z)
• CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models [77.45934004406283]
  We systematically study decompounding, the task of splitting compound words into their constituents. We introduce a dataset of 255k compound and non-compound words across 56 diverse languages obtained from Wiktionary. We introduce a novel methodology to train dedicated models for decompounding.
  arXiv  Detail & Related papers  (2023-05-23T16:32:27Z)
• CLSE: Corpus of Linguistically Significant Entities [58.29901964387952]
  We release a Corpus of Linguistically Significant Entities (CLSE) annotated by experts. CLSE covers 74 different semantic types to support various applications from airline ticketing to video games. We create a linguistically representative NLG evaluation benchmark in three languages: French, Marathi, and Russian.
  arXiv  Detail & Related papers  (2022-11-04T12:56:12Z)
• Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification [0.27998963147546146]
  Complex word identification (CWI) is a cornerstone process towards proper text simplification. CWI is highly dependent on context, whereas its difficulty is augmented by the scarcity of available datasets. We propose a novel training technique for the CWI task based on domain adaptation to improve the target character and context representations.
  arXiv  Detail & Related papers  (2022-05-15T13:21:02Z)
• Structured Prediction as Translation between Augmented Natural Languages [109.50236248762877]
  We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks. Instead of tackling the problem by training task-specific discriminatives, we frame it as a translation task between augmented natural languages. Our approach can match or outperform task-specific models on all tasks, and in particular, achieves new state-of-the-art results on joint entity and relation extraction.
  arXiv  Detail & Related papers  (2021-01-14T18:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.