Zobrazeno 1 - 10
of 411
pro vyhledávání: '"Gordon, Mitchell"'
StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
Autor:
Fisher, Jillian, Hallinan, Skyler, Lu, Ximing, Gordon, Mitchell, Harchaoui, Zaid, Choi, Yejin
Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring author-sp
Externí odkaz:
http://arxiv.org/abs/2408.15666
Trained on vast corpora, Large Language Models (LLMs) have the potential to encode visualization design knowledge and best practices. However, if they fail to do so, they might provide unreliable visualization recommendations. What visualization desi
Externí odkaz:
http://arxiv.org/abs/2408.06845
Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components, gradients of memo
Externí odkaz:
http://arxiv.org/abs/2403.19851
Autor:
Sorensen, Taylor, Moore, Jared, Fisher, Jillian, Gordon, Mitchell, Mireshghallah, Niloofar, Rytting, Christopher Michael, Ye, Andre, Jiang, Liwei, Lu, Ximing, Dziri, Nouha, Althoff, Tim, Choi, Yejin
With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an open resea
Externí odkaz:
http://arxiv.org/abs/2402.05070
How can online communities execute a focused vision for their space? Curation offers one approach, where community leaders manually select content to share with the community. Curation enables leaders to shape a space that matches their taste, norms,
Externí odkaz:
http://arxiv.org/abs/2308.13841
Autor:
SMITH, GORDON MITCHELL
Publikováno v:
Ploughshares, 2023 Dec 01. 49(4), 164-164.
Externí odkaz:
https://www.jstor.org/stable/27274939
Autor:
Lianjie Qin, Laiyin Zhu, Baoyin Liu, Zixuan Li, Yugang Tian, Gordon Mitchell, Shifei Shen, Wei Xu, Jianguo Chen
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-10 (2024)
Abstract Precipitation from tropical cyclones (TCs) can cause massive damage from inland floods and is becoming more intense under a warming climate. However, knowledge gaps still exist in changes of spatial patterns in heavy TC precipitation. Here w
Externí odkaz:
https://doaj.org/article/53beb405ebf3470a841ebbc32b0ee2ff
Autor:
Chanover, Nancy J., Bauer, James M., Blalock, John J., Gordon, Mitchell K., Huber, Lyle F., Mace, Mia J. T., Neakrase, Lynn D. V., Tiscareno, Matthew S., Walker, Raymond J.
While there have been far fewer missions to the outer Solar System than to the inner Solar System, spacecraft destined for the giant planets have conducted a wide range of fundamental investigations, returning data that continues to reshape our under
Externí odkaz:
http://arxiv.org/abs/2212.02492
Autor:
Gordon, Mitchell L., Lam, Michelle S., Park, Joon Sung, Patel, Kayur, Hancock, Jeffrey T., Hashimoto, Tatsunori, Bernstein, Michael S.
Whose labels should a machine learning (ML) algorithm learn to emulate? For ML tasks ranging from online comment toxicity to misinformation detection to medical diagnosis, different groups in society may have irreconcilable disagreements about ground
Externí odkaz:
http://arxiv.org/abs/2202.02950