Dataset Groups Activity Stream Self-Recognition in Language Models A self-recognition test for language models using model-generated security questions. BibTex: @dataset{Tim_R_Davidson_and_Viacheslav_Surkov_and_Veniamin_Veselovsky_and_Giuseppe_Russo_and_Robert_West_and_Caglar_Gulcehre_2024, abstract = {A self-recognition test for language models using model-generated security questions.}, author = {Tim R. Davidson and Viacheslav Surkov and Veniamin Veselovsky and Giuseppe Russo and Robert West and Caglar Gulcehre}, doi = {10.57702/5b1knu04}, institution = {No Organization}, keyword = {'language models', 'security questions', 'self-recognition'}, month = {dec}, publisher = {TIB}, title = {Self-Recognition in Language Models}, url = {https://service.tib.eu/ldmservice/dataset/self-recognition-in-language-models}, year = {2024} }
