It’s All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models
Year: 2026
Type: conference-paper
Abstract: Despite the recent advancements in NLP with the advent of Large Language Models (LLMs), Entity Linking (EL) for historical texts remains challenging due to linguistic variation, noisy inputs, and evolving semantic conventions.Existing solutions either require substantial training data or rely on domain-specific rules that limit scalability.In this paper, we present MHEL-LLaMo (Multilingual Historical Entity Linking with Large Language MOdels), 1 an unsupervised ensemble approach combining a Small Language Model (SLM) and an LLM.MHEL-LLaMo leverages a multilingual bi-encoder (BELA) for candidate retrieval and an instruction-tuned LLM for NIL prediction and candidate selection via prompt chaining.Our system uses the SLM's confidence scores to discriminate between easy and hard samples, applying an LLM only for hard cases.This strategy reduces computational cost while preventing hallucinations on straightforward cases.We evaluate MHEL-LLaMo on four established benchmarks in six European languages (English, Finnish, French, German, Italian and Swedish) from the 19th and 20th centuries.Results demonstrate that MHEL-LLaMo outperforms state-of-the-art models without requiring fine-tuning, offering a scalable solution for lowresource historical EL.The implementation of MHEL-LLaMo is available on Github.
Institutions: Télécom Paris, University of Macerata, KNAW Humanities Cluster
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G8519274658
OpenAlex ID: W7140125440