Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Zhang, Heidi"'
Model checklists (Ribeiro et al., 2020) have emerged as a useful tool for understanding the behavior of LLMs, analogous to unit-testing in software engineering. However, despite datasets being a key determinant of model behavior, evaluating datasets,
Externí odkaz:
http://arxiv.org/abs/2408.02919
Autor:
Zhang, Heidi C., Semnani, Sina J., Ghassemi, Farhad, Xu, Jialiang, Liu, Shicheng, Lam, Monica S.
We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge
Externí odkaz:
http://arxiv.org/abs/2406.00562
Autor:
Anwar, Usman, Saparov, Abulhair, Rando, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Lubana, Ekdeep Singh, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L., Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi, Zhong, Ruiqi, hÉigeartaigh, Seán Ó, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Petrov, Aleksandar, de Witt, Christian Schroeder, Motwan, Sumeet Ramesh, Bengio, Yoshua, Chen, Danqi, Torr, Philip H. S., Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob, Tramer, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods
Externí odkaz:
http://arxiv.org/abs/2404.09932
Autor:
Tan, Weiting, Chen, Yunmo, Chen, Tongfei, Qin, Guanghui, Xu, Haoran, Zhang, Heidi C., Van Durme, Benjamin, Koehn, Philipp
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representa
Externí odkaz:
http://arxiv.org/abs/2402.01172
This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus. WikiChat generates a response
Externí odkaz:
http://arxiv.org/abs/2305.14292
Publikováno v:
In Current Opinion in Biomedical Engineering December 2021 20
Autor:
Zhang, Heidi
Publikováno v:
The British Journal of Social Work, 2018 Jan 01. 48(1), 124-140.
Externí odkaz:
https://www.jstor.org/stable/26612967
Despite recent advances in Large Language Models (LLMs), users still cannot trust the information provided in their responses. LLMs cannot speak accurately about events that occurred after their training, which are often topics of great interest to u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6637ce5356ed3dfa4835978c09419271
Autor:
Whiteaker, Jeffrey R., Zhao, Lei, Zhang, Heidi Y., Feng, Li-Chia, Piening, Brian D., Anderson, Leigh, Paulovich, Amanda G.
Publikováno v:
In Analytical Biochemistry 2007 362(1):44-54
Autor:
Zhang, Heidi
Publikováno v:
Canadian Review of Social Policy, 2018 Oct 01. 78, 111-115.
Externí odkaz:
https://www.jstor.org/stable/48695942