*Workshop co-located with EACL, 24-29 March 2026, Rabat, Morocco*
LLMs in so many languages? When can such a claim be substantiated, and how should it be evaluated? This workshop brings together the community to answer these questions through three goals:
– Establish a dedicated venue for multilingual evaluation, including resources, metrics, and methodologies;
– Advance and standardize evaluation practices to enhance accuracy, scalability, fairness, and cross-system comparability;
– Integrate cultural and social dimensions into multilingual evaluation.
*Call for Papers*
We invite archival (ACL Anthology) or non-archival submissions, in ACL’s short or long format. We accept both direct and ARR-reviewed submissions. Topics include, but are not limited to:
– Evaluation resources beyond English or Western-centric perspectives and materials;
– Annotation methodology and procedures;
– Standardised reporting, and scientific comparison of multilingual performance;
– Evaluation protocols: ranking vs direct assessment, rubric-based vs reference-based vs reference-free, prompt variations, etc;
– Metrics, LLM judges, and reward models;
– Complex tasks: multimodality, fairness, long I/O, tool using, code-switching, literary, etc;
– Sociocultural and cognitive variation affecting the use and evaluation across languages;
– Scalable evaluation of cultural and factual knowledge;
– Efficient evaluation of a massive number of languages and tasks;
– AI-assisted evaluation: data, methods, metrics, and standards;
– Other position, application-, or theory-focused contributions.
*Dates* (tentative, all dates are 23:59 AoE)
– Direct submission deadline: 19 Dec 2025
– Pre-reviewed ARR submission deadline: 02 Jan 2026
– Notification of acceptance: 23 Jan 2026
– Camera-ready version due: 03 Feb 2026
– Workshop date: 28 or 29 Mar 2026
Website: https://multilingual-multicultural-evaluation.github.io/
Email: mme-workshop@googlegroups.com
Submission: OpenReview, link TBD