← Back to all news
arXiv Computation and Language

EnsembleLink: Accurate Record Linkage Without Training Data

EnsembleLink is a record‑linkage method that achieves high accuracy without requiring any training labels. It uses pre‑trained language models to capture semantic relationships, enabling it to match records across diverse domains such as city names, person names, organizations, multilingual political parties, and bibliographic entries. The approach runs locally on open‑source models, avoiding external API calls, and completes typical linkage tasks in minutes.

Related stories

arXiv Computation and Language
4d ago

Pre-Trained Language Models as Zero-Shot Tools for Social Science Research

The paper demonstrates that pre‑trained language models can perform record linkage and demographic inference from names without task‑specific training. EnsembleLink, an algorithm that combines pre‑trained embeddings with string‑based scorers, achieves performance comparable to or better than prior methods across diverse scripts and formats. Large language models reach up to 83.8% accuracy on U.S. voter files for ethnicity inference, surpassing name‑supplemented BISG and enabling inference for non‑U.S. ethnic categories while reducing bias in geographic racial gap estimates.

By Noah Dasanaike
llmsragsafety
More like this →
arXiv Computation and Language
Sep 11

Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking

The paper introduces a new perspective on entity rarity in multimodal entity linking by using knowledge‑graph structural metrics instead of popularity metrics, revealing many rare entities previously overlooked. Experiments show that state‑of‑the‑art models suffer a 15.4–39.9% accuracy drop on these rare‑entity slices. The authors propose a training‑free framework that combines reasoning and retrieval with a vision‑language model, achieving a 6.9% overall accuracy gain and up to 23.3% improvement on rare entities, and release a new benchmark MERLIN‑Rare for focused evaluation.

By Parinthapat Pengpun, Simran Khanuja, Graham Neubig
llmsmultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 14

Extracting Dataset Mentions in Forced Displacement and FCV Documents: A Weakly Supervised Framework with LLM-Based Label Refinement

The paper introduces a weakly supervised framework for extracting dataset mentions from forced displacement and Fragile, Conflict, and Violence (FCV) documents. It uses a lightweight model trained on general research literature to generate candidate mentions, which are then refined by a large language model that validates or rejects them and corrects boundaries. The refined annotations are augmented with synthetic and contrastive examples to fine‑tune the model, achieving 74.1% precision and 70.5% recall on a benchmark of 1,706 passages, with higher precision (89.5%) on passages that contain dataset references.

By Rafael Macalaba, Aivin V. Solatorio, Patrick Michael Brock, Olivier Dupriez
llmsfine-tuningbenchmarks
More like this →
arXiv AI
Sep 3

Direct Construction of Disambiguated Knowledge Bases from Large Language Models

The paper introduces GPTKB 2.0, a method for building disambiguated knowledge bases directly from large language models. It addresses the lack of native entity representation in LLMs by performing on‑the‑fly disambiguation of entities, relations, and classes, achieving a million‑scale KB with over 1 million disambiguated entities and 38.4 million triples. The authors analyze trade‑offs among accuracy, scale, and cost, and release the system at https://gptkb.org/.

By Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski
llmsragnlp
More like this →
arXiv AI
Sep 3

BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision

BioELX is a retrieve‑rerank framework for cross‑lingual biomedical entity linking that tackles two key problems: the English‑biased UMLS alias training data and the degradation caused by naïvely adding context. It fine‑tunes SapBERT_multi with Wikidata‑derived cross‑lingual alias supervision to create shared concept neighborhoods, and then reranks candidates using pretrained LLMs with mention‑anchored prompting to focus on the target mention. Experiments demonstrate state‑of‑the‑art performance on four benchmarks, improving Recall@1 by 4.8–18.2 percentage points without task‑specific annotations.

By Yi Wang, Corina Dima, Liangyu Zhong, Steffen Staab
llmsragnlpbenchmarks
More like this →