Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Huang, Saffron"'
Autor:
Huang, Saffron, Siddarth, Divya, Lovitt, Liane, Liao, Thomas I., Durmus, Esin, Tamkin, Alex, Ganguli, Deep
Publikováno v:
Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency. 1395-1417
There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To address th
Externí odkaz:
http://arxiv.org/abs/2406.07814
Model evaluations are central to understanding the safety, risks, and societal impacts of AI systems. While most real-world AI applications involve human-AI interaction, most current evaluations (e.g., common benchmarks) of AI models do not. Instead,
Externí odkaz:
http://arxiv.org/abs/2405.10632
Autor:
Huang, Saffron, author, Siddarth, Divya, author
Publikováno v:
AI Morality, 2024.
Externí odkaz:
https://doi.org/10.1093/oso/9780198876434.003.0007
Autor:
Huang, Saffron, Siddarth, Divya
Many generative foundation models (or GFMs) are trained on publicly available data and use public infrastructure, but 1) may degrade the "digital commons" that they depend on, and 2) do not have processes in place to return value captured to data pro
Externí odkaz:
http://arxiv.org/abs/2303.11074
Autor:
Perez, Ethan, Huang, Saffron, Song, Francis, Cai, Trevor, Ring, Roman, Aslanides, John, Glaese, Amelia, McAleese, Nat, Irving, Geoffrey
Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human annotation i
Externí odkaz:
http://arxiv.org/abs/2202.03286
Autor:
Rae, Jack W., Borgeaud, Sebastian, Cai, Trevor, Millican, Katie, Hoffmann, Jordan, Song, Francis, Aslanides, John, Henderson, Sarah, Ring, Roman, Young, Susannah, Rutherford, Eliza, Hennigan, Tom, Menick, Jacob, Cassirer, Albin, Powell, Richard, Driessche, George van den, Hendricks, Lisa Anne, Rauh, Maribeth, Huang, Po-Sen, Glaese, Amelia, Welbl, Johannes, Dathathri, Sumanth, Huang, Saffron, Uesato, Jonathan, Mellor, John, Higgins, Irina, Creswell, Antonia, McAleese, Nat, Wu, Amy, Elsen, Erich, Jayakumar, Siddhant, Buchatskaya, Elena, Budden, David, Sutherland, Esme, Simonyan, Karen, Paganini, Michela, Sifre, Laurent, Martens, Lena, Li, Xiang Lorraine, Kuncoro, Adhiguna, Nematzadeh, Aida, Gribovskaya, Elena, Donato, Domenic, Lazaridou, Angeliki, Mensch, Arthur, Lespiau, Jean-Baptiste, Tsimpoukelli, Maria, Grigorev, Nikolai, Fritz, Doug, Sottiaux, Thibault, Pajarskas, Mantas, Pohlen, Toby, Gong, Zhitao, Toyama, Daniel, d'Autume, Cyprien de Masson, Li, Yujia, Terzi, Tayfun, Mikulik, Vladimir, Babuschkin, Igor, Clark, Aidan, Casas, Diego de Las, Guy, Aurelia, Jones, Chris, Bradbury, James, Johnson, Matthew, Hechtman, Blake, Weidinger, Laura, Gabriel, Iason, Isaac, William, Lockhart, Ed, Osindero, Simon, Rimell, Laura, Dyer, Chris, Vinyals, Oriol, Ayoub, Kareem, Stanway, Jeff, Bennett, Lorrayne, Hassabis, Demis, Kavukcuoglu, Koray, Irving, Geoffrey
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language m
Externí odkaz:
http://arxiv.org/abs/2112.11446
Autor:
Borgeaud, Sebastian, Mensch, Arthur, Hoffmann, Jordan, Cai, Trevor, Rutherford, Eliza, Millican, Katie, Driessche, George van den, Lespiau, Jean-Baptiste, Damoc, Bogdan, Clark, Aidan, Casas, Diego de Las, Guy, Aurelia, Menick, Jacob, Ring, Roman, Hennigan, Tom, Huang, Saffron, Maggiore, Loren, Jones, Chris, Cassirer, Albin, Brock, Andy, Paganini, Michela, Irving, Geoffrey, Vinyals, Oriol, Osindero, Simon, Simonyan, Karen, Rae, Jack W., Elsen, Erich, Sifre, Laurent
We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO) obtains compa
Externí odkaz:
http://arxiv.org/abs/2112.04426
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.