The CLEF-2026 CheckThat! Lab: Advancing Multilingual Fact-Checking

TL;DR

The paper presents the CLEF-2026 CheckThat! Lab edition, advancing the verification pipeline through three tasks: source retrieval for scientific web claims, fact-checking of numerical and temporal claims with reasoning traces via a test-time scaling framework, and automatic generation of full fact-checking articles. It covers five languages (Arabic, English, German, French, Spanish) and provides multilingual data, benchmarks, and evaluation protocols for retrieval, reasoning, and long-form justification generation. Key contributions include an end-to-end pipeline from check-worthiness to article generation, with evaluation metrics such as $MRR@5$, $Recall@k$, $F_1$ variants, and entailment/citation quality. The work targets practical impact for professional fact-checkers and journalists by enabling scalable, multilingual verification workflows aligned with real-world needs.

Abstract

The CheckThat! lab aims to advance the development of innovative technologies combating disinformation and manipulation efforts in online communication across a multitude of languages and platforms. While in early editions the focus has been on core tasks of the verification pipeline (check-worthiness, evidence retrieval, and verification), in the past three editions, the lab added additional tasks linked to the verification process. In this year's edition, the verification pipeline is at the center again with the following tasks: Task 1 on source retrieval for scientific web claims (a follow-up of the 2025 edition), Task 2 on fact-checking numerical and temporal claims, which adds a reasoning component to the 2025 edition, and Task 3, which expands the verification pipeline with generation of full-fact-checking articles. These tasks represent challenging classification and retrieval problems as well as generation challenges at the document and span level, including multilingual settings.

Figures (1)

• Figure 1: Overview of the CheckThat! verification pipeline, which features the core fact-checking tasks along with the tasks we address in the 2026 edition of the lab.