{"url":"/dataset/climabench","name":"Climabench","full_name":null,"description_markdown":"The topic of Climate Change (CC) has received limited attention in NLP despite its real world urgency. Activists and policy-makers need NLP tools in order to effectively process the vast and rapidly growing textual data produced on CC. Their utility, however, primarily depends on whether the current state-of-the-art models can generalize across various tasks in the CC domain. In order to address this gap, we introduce Climate Change Benchmark (ClimaBench), a benchmark collection of existing disparate datasets for evaluating model performance across a diverse set of CC NLU tasks systematically. Further, we enhance the benchmark by releasing two large-scale labelled text classification and question-answering datasets curated from publicly available environmental disclosures. Lastly, we provide an analysis of several generic and CC-oriented models answering whether fine-tuning on domain text offers any improvements across these tasks. We hope this work provides a standard assessment tool for research on CC text data.","description_withheld":null,"homepage":"https://huggingface.co/datasets/iceberg-nlp/climabench","introduced_date":"2023-01-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/climabench-a-benchmark-dataset-for-climate","title":"Towards Answering Climate Questionnaires from Unstructured Climate Reports","first_author":"Daniel Spokoyny","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Climabench"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/iceberg-nlp/climabench","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-climabench","task":"Text Classification","dataset_variant":"Climabench","rows":8,"metrics":["Evaluation Macro F1"],"first_row_in_archive_order":{"model":"CliReBERT (P0L3/clirebert_clirevocab_uncased)","paper":"/paper/climate-research-domain-berts-pretraining","metrics":{"Evaluation Macro F1":"0.6545"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/climate-research-domain-berts-pretraining","title":"Climate Research Domain BERTs: Pretraining, Adaptation, and Evaluation","date":"2025-05-19","rows_on_this_dataset":8,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}