evaluation

Multimodal generation and retrieval systems are increasingly central to modern information retrieval, powering retrieval-augmented generation (RAG), multimodal search, recommendation, and knowledge-intensive applications. Despite rapid progress in multimodal large language models (MLLMs), robust and principled evaluation of multimodal generation and retrieval remains a major open challenge for the IR community.

The fifth edition of the Natural Language Generation, Evaluation, and Metrics (GEM) Workshop will be at ACL 2026 in San Diego!

HIPE-2026 Shared Task - CALL FOR PARTICIPATION (apologies for cross-postings)

SIGTURK—
The Second Workshop on
Natural Language Processing for Turkic Languages
At EACL 2026

Rabat, Morocco
March 28-29, 2026[1]

# Introduciton

We are excited to announce the Second Meeting of the ACL Special
Interest Group on Turkic Languages, held in conjunction with The 19th
Conference of the European Chapter of the Association for Computational
Linguistics (EACL 2026), Rabat, Morocco.

We are pleased to announce SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures.

This task extends BLEnD (Myung et al., 2024), a hand-crafted benchmark built by native speakers to evaluate cultural knowledge in large language models (LLMs) and NLP systems,to more than 30 language-culture pairs. The goal is to evaluate models and provide insights for improving cross-cultural performance.

https://uncertainlp.github.io/

UPDATE: We extended submission deadlines by one week! They are now August 15th for direct submissions and August 29th for submissions with already existing ACL Rolling Reviews (ARR).

https://uncertainlp.github.io/

Human languages are inherently ambiguous and understanding language input is subject to interpretation and complex contextual dependencies. Nevertheless, the main body of research in NLP is still based on the assumption that ambiguities and other types of underspecification can and have to be resolved. This workshop will provide a platform for research that embraces variability in human language and aims to represent and evaluate the uncertainty that arises from it, and from modeling tools themselves.

https://uncertainlp.github.io/

Human languages are inherently ambiguous and understanding language input is subject to interpretation and complex contextual dependencies. Nevertheless, the main body of research in NLP is still based on the assumption that ambiguities and other types of underspecification can and have to be resolved. This workshop will provide a platform for research that embraces variability in human language and aims to represent and evaluate the uncertainty that arises from it, and from modeling tools themselves.

Description

The demand for more sophisticated natural human-computer and human-robot interactions is rapidly increasing as users become more accustomed to conversation-like interactions with AI and NLP systems. Such interactions require not only the robust recognition and generation of expressions through multiple modalities (language, gesture, vision, action, etc.), but also the encoding of situated meaning.