Dataset Groups Activity Stream FKTC FKTC is a test set for evaluating the factual knowledge of large language models. It contains 210,158 prompts in total. BibTex: @dataset{Weixuan_Wang_and_Barry_Haddow_and_Alexandra_Birch_and_Wei_Peng_2024, abstract = {FKTC is a test set for evaluating the factual knowledge of large language models. It contains 210,158 prompts in total.}, author = {Weixuan Wang and Barry Haddow and Alexandra Birch and Wei Peng}, doi = {10.57702/b238f8y2}, institution = {No Organization}, keyword = {'factual knowledge', 'large language models', 'question answering'}, month = {dec}, publisher = {TIB}, title = {FKTC}, url = {https://service.tib.eu/ldmservice/dataset/fktc}, year = {2024} }
