LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation

Haffoudhi, Samy; Dobričić, Nikola; Suchanek, Fabian; Holzenberger, Nils

doi:10.24963/ijcai.2026/966

LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation

Samy Haffoudhi, Nikola Dobričić, Fabian Suchanek, Nils Holzenberger

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8401-8405.

https://doi.org/10.24963/ijcai.2026/966

Keywords

AI: Natural Language Processing

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-to-end 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. All code is publicly available at https://github.com/dig-team/LELA, and a video is at https://www.youtube.com/watch?v=WdupiRjLbR4.

Samy Haffoudhi, Nikola Dobričić, Fabian Suchanek, and Nils Holzenberger. 2026. LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8401–8405. https://doi.org/10.24963/ijcai.2026/966

@inproceedings{ijcai2026p966,
  title     = {LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation},
  author    = {Haffoudhi, Samy and Dobričić, Nikola and Suchanek, Fabian and Holzenberger, Nils},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8401--8405},
  year      = {2026},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2026/966},
  url       = {https://doi.org/10.24963/ijcai.2026/966},
}

TY  - CPAPER
TI  - LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
AU  - Haffoudhi, Samy
AU  - Dobričić, Nikola
AU  - Suchanek, Fabian
AU  - Holzenberger, Nils
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8401
EP  - 8405
DO  - 10.24963/ijcai.2026/966
UR  - https://doi.org/10.24963/ijcai.2026/966
ER  -