ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims
This work addresses the problem of climate disinformation for researchers and fact-checkers, but it is incremental as it builds on a prior shared task with expanded data and a new classification task.
The paper tackles the challenge of automatically verifying climate-related claims against scientific literature and classifying disinformation narratives, expanding on a previous shared task with tripled training data and a new classification component. It attracted 20 participants, with systems using dense retrieval, cross-encoder ensembles, and large language models, and introduced an automated framework to assess retrieval quality, revealing biases in conventional metrics and that not all disinformation is equally verifiable.
Automatically verifying climate-related claims against scientific literature is a challenging task, complicated by the specialised nature of scholarly evidence and the diversity of rhetorical strategies underlying climate disinformation. ClimateCheck 2026 is the second iteration of a shared task addressing this challenge, expanding on the 2025 edition with tripled training data and a new disinformation narrative classification task. Running from January to February 2026 on the CodaBench platform, the competition attracted 20 registered participants and 8 leaderboard submissions, with systems combining dense retrieval pipelines, cross-encoder ensembles, and large language models with structured hierarchical reasoning. In addition to standard evaluation metrics (Recall@K and Binary Preference), we adapt an automated framework to assess retrieval quality under incomplete annotations, exposing systematic biases in how conventional metrics rank systems. A cross-task analysis further reveals that not all climate disinformation is equally verifiable, potentially implicating how future fact-checking systems should be designed.