Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Street, Winnie"'
Autor:
Keeling, Geoff, Street, Winnie, Stachaczyk, Martyna, Zakharova, Daria, Comsa, Iulia M., Sakovych, Anastasiya, Logothesis, Isabella, Zhang, Zejia, Arcas, Blaise Agüera y, Birch, Jonathan
Pleasure and pain play an important role in human decision making by providing a common currency for resolving motivational conflicts. While Large Language Models (LLMs) can generate detailed descriptions of pleasure and pain experiences, it is an op
Externí odkaz:
http://arxiv.org/abs/2411.02432
Autor:
Keeling, Geoff, Street, Winnie
Credences are mental states corresponding to degrees of confidence in propositions. Attribution of credences to Large Language Models (LLMs) is commonplace in the empirical literature on LLM evaluation. Yet the theoretical basis for LLM credence attr
Externí odkaz:
http://arxiv.org/abs/2407.08388
Autor:
Street, Winnie, Siy, John Oliver, Keeling, Geoff, Baranes, Adrien, Barnett, Benjamin, McKibben, Michael, Kanyere, Tatenda, Lentz, Alison, Arcas, Blaise Aguera y, Dunbar, Robin I. M.
This paper examines the extent to which large language models (LLMs) have developed higher-order theory of mind (ToM); the human ability to reason about multiple mental and emotional states in a recursive manner (e.g. I think that you believe that sh
Externí odkaz:
http://arxiv.org/abs/2405.18870
Autor:
Street, Winnie
Publikováno v:
Proceedings of Workshop on Theory of Mind in Human-AI Interaction at CHI 2024 (ToMinHAI at CHI 2024)
Large language models (LLMs) are transforming human-computer interaction and conceptions of artificial intelligence (AI) with their impressive capacities for conversing and reasoning in natural language. There is growing interest in whether LLMs have
Externí odkaz:
http://arxiv.org/abs/2405.08154
Autor:
Gabriel, Iason, Manzini, Arianna, Keeling, Geoff, Hendricks, Lisa Anne, Rieser, Verena, Iqbal, Hasan, Tomašev, Nenad, Ktena, Ira, Kenton, Zachary, Rodriguez, Mikel, El-Sayed, Seliem, Brown, Sasha, Akbulut, Canfer, Trask, Andrew, Hughes, Edward, Bergman, A. Stevie, Shelby, Renee, Marchal, Nahema, Griffin, Conor, Mateos-Garcia, Juan, Weidinger, Laura, Street, Winnie, Lange, Benjamin, Ingerman, Alex, Lentz, Alison, Enger, Reed, Barakat, Andrew, Krakovna, Victoria, Siy, John Oliver, Kurth-Nelson, Zeb, McCroskery, Amanda, Bolina, Vijay, Law, Harry, Shanahan, Murray, Alberts, Lize, Balle, Borja, de Haas, Sarah, Ibitoye, Yetunde, Dafoe, Allan, Goldberg, Beth, Krier, Sébastien, Reese, Alexander, Witherspoon, Sims, Hawkins, Will, Rauh, Maribeth, Wallace, Don, Franklin, Matija, Goldstein, Josh A., Lehman, Joel, Klenk, Michael, Vallor, Shannon, Biles, Courtney, Morris, Meredith Ringel, King, Helen, Arcas, Blaise Agüera y, Isaac, William, Manyika, James
This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute sequences of act
Externí odkaz:
http://arxiv.org/abs/2404.16244