Renaissance Labs

Atlas / Europe

Nonprofit · Alicante, Spain

ELLIS Alicante

ELLIS Alicante is a non-profit unit of the European ELLIS network focused on ethical, human-centric AI, directed by Nuria Oliver.

responsible AI

Alicante, Spain

Founded
2020
Type
Nonprofit
Based in
Alicante, Spain
Featured projects
4

About

ELLIS Alicante was founded in 2020 as a foundation hosting a research unit of the ELLIS network in Spain. It resulted from a 2019 bid, led by Nuria Oliver, for Alicante to host an ELLIS unit, and she serves as its director.

Its research addresses modeling human behavior at individual and societal scales, systems that interact naturally with people, and ethical AI covering fairness, privacy and transparency. It is funded by the Generalitat Valenciana, the European Regional Development Fund and partners including Intel and Fundación Banco Sabadell, and reports over 38 million euros in EU project budgets.

Paper code and evaluation repositories are published on GitHub, including tutorials on graph rewiring and fairness, an open framework for social media AR filters, and evaluations of how language models handle mental-health crises.

Mission and ambitions

To advance ethical, responsible and human-centric artificial intelligence that serves society.

Known for

  1. 01

    Human-centric and ethical AI research

  2. 02

    Directed by Nuria Oliver

  3. 03

    Open benchmarks on fairness and LLM safety

Milestones

  1. 2019

    Alicante wins an ELLIS unit

    A bid led by Nuria Oliver brought a unit of the ELLIS network to Alicante.

  2. 2020

    ELLIS Alicante foundation established

    The foundation began operating and opened its GitHub organization in April 2020.

  3. 2022

    OpenFilter framework

    The group released a framework to democratize research access to social media AR filters, with Piera Riccio, Nuria Oliver and coauthors.

  4. 2022

    Graph rewiring tutorial

    A tutorial on graph rewiring and fairness was presented at the Learning on Graphs conference.

  5. 2025

    Multilingual and multimodal red teaming

    Code accompanying a paper on red teaming multimodal models was presented at the ACL 2025 LLM security workshop.

  6. 2025

    LLM mental-health crisis evaluation

    An evaluation of how large language models handle mental-health crises was published with open code.

Open source

GitHubgithub.com/ellisalicante
  • This repository holds code and other relevant files for the Learning on Graphs 2022 (LoG) tutorial "Graph Rewi (54 stars)

  • This repository refers to the paper currently under review for the 36th Conference on Neural Information Proce (13 stars)

  • JMIR MH 2026 - "Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs" Adrian Arnaiz-R (9 stars)

  • Repository accompanying our paper titled "Beyond Words: Multilingual and Multimodal Red Teaming of MLLMs", pre (3 stars)

Notable releases

Openness

Paper code and evaluation repositories are public on GitHub.

People

Listed from the lab's own pages and public profiles.

Contact and community

Contact via site.

Sources

Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.

Labs nearby