Dataset Groups Activity Stream harmless/harmful anchor datasets This dataset contains 100 harmless and 100 harmful anchor prompts for evaluating the performance of large language models. BibTex: @dataset{Zheng_et_al_2024, abstract = {This dataset contains 100 harmless and 100 harmful anchor prompts for evaluating the performance of large language models.}, author = {Zheng et al.}, doi = {10.57702/g83nrnnd}, institution = {No Organization}, keyword = {'anchor prompts', 'harmful', 'harmless'}, month = {dec}, publisher = {TIB}, title = {harmless/harmful anchor datasets}, url = {https://service.tib.eu/ldmservice/dataset/harmless-harmful-anchor-datasets}, year = {2024} }
