LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
Summary
LELA is an LLM-based entity linking framework that combines zero-shot NER and entity disambiguation into an end-to-end Python library, validated across diverse settings.
View Cached Full Text
Cached at: 05/27/26, 09:10 AM
# LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation Source: [https://arxiv.org/abs/2605.26956](https://arxiv.org/abs/2605.26956) [View PDF](https://arxiv.org/pdf/2605.26956) > Abstract:Entity linking is a key component of many downstream NLP systems, yet existing approaches are often tied to the specific target knowledge bases and domains, limiting their real world application\. In this paper, we extend LELA, a modular and domain\-agnostic LLM\-based entity disambiguation method, into a practical Python library that integrates zero\-shot Named Entity Recognition \(NER\) \-thereby providing a complete end\-toend pipeline for entity\-linking in real\-world usage\. We provide experimental results validating LELA's performance and robustness across diverse entity linking settings\. In our demo, users can play with the system on their own input texts\. ## Submission history From: Samy Haffoudhi \[[view email](https://arxiv.org/show-email/4237fb9a/2605.26956)\] \[via CCSD proxy\] **\[v1\]**Tue, 26 May 2026 12:45:35 UTC \(609 KB\)
Similar Articles
Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking
The paper introduces Sci-ZSEL, a cost-efficient zero-shot scientific entity linking framework that selectively uses LLMs and an ontology-aware filter to enhance performance on benchmarks with low lexical overlap.
LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English
LLMBridge introduces an LLM-based pipeline for end-to-end referential bridging resolution, achieving state-of-the-art performance on three English datasets. The system combines heuristic pre/post-processing with LLM natural language inference.
DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models
Introduces DE-NER, a dialogue elicitation framework for zero-shot named entity recognition that uses self-play between questioner and roleplayer LLMs to clarify entity boundaries, achieving an average 3.75% F1 improvement over baselines.
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
The paper evaluates when zero-shot LLMs can replace fine-tuned NLU classifiers for intent detection in production, highlighting LLM advantages in out-of-scope detection, ASR robustness, and dynamic schemas, and offers a decision framework for practitioners.
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
This paper introduces LEAP, a training-free method to accelerate inference in Diffusion Language Models (dLLMs) by detecting early-converging tokens, reducing denoising steps by 30% without losing accuracy.