Zobrazeno 1 - 10
of 924
pro vyhledávání: '"Ungar, Lyle"'
Autor:
Jin, Helen, Havaldar, Shreya, Kim, Chaehyeon, Xue, Anton, You, Weiqiu, Qu, Helen, Gatti, Marco, Hashimoto, Daniel A, Jain, Bhuvnesh, Madani, Amin, Sako, Masao, Ungar, Lyle, Wong, Eric
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional data, and it can be hard even
Externí odkaz:
http://arxiv.org/abs/2409.13684
Large Language Models (LLMs), which simulate human users, are frequently employed to evaluate chatbots in applications such as tutoring and customer service. Effective evaluation necessitates a high degree of human-like diversity within these simulat
Externí odkaz:
http://arxiv.org/abs/2409.00262
Autor:
Giorgi, Salvatore, Liu, Tingting, Aich, Ankit, Isman, Kelsey, Sherman, Garrick, Fried, Zachary, Sedoc, João, Ungar, Lyle H., Curtis, Brenda
Large language models (LLMs) are increasingly being used in human-centered social scientific tasks, such as data annotation, synthetic data creation, and engaging in dialog. However, these tasks are highly subjective and dependent on human factors, s
Externí odkaz:
http://arxiv.org/abs/2406.14462
Large Language Models (LLMs) are increasingly being used in educational and learning applications. Research has demonstrated that controlling for style, to fit the needs of the learner, fosters increased understanding, promotes inclusion, and helps w
Externí odkaz:
http://arxiv.org/abs/2406.12679
Autor:
Havaldar, Shreya, Giorgi, Salvatore, Rai, Sunny, Talhelm, Thomas, Guntuku, Sharath Chandra, Ungar, Lyle
Cultural variation exists between nations (e.g., the United States vs. China), but also within regions (e.g., California vs. Texas, Los Angeles vs. San Francisco). Measuring this regional cultural variation can illuminate how and why people think and
Externí odkaz:
http://arxiv.org/abs/2406.11622
Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking how a model's output is influenced when we fine-tune on a new training
Externí odkaz:
http://arxiv.org/abs/2406.00509
Autor:
Salecha, Aadesh, Ireland, Molly E., Subrahmanya, Shashanka, Sedoc, João, Ungar, Lyle H., Eichstaedt, Johannes C.
As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously undetected soci
Externí odkaz:
http://arxiv.org/abs/2405.06058
Autor:
Himelein-Wachowiak, McKenzie, Giorgi, Salvatore, Devoto, Amanda, Rahman, Muhammad, Ungar, Lyle, Schwartz, H Andrew, Epstein, David H, Leggio, Lorenzo, Curtis, Brenda
Publikováno v:
Journal of Medical Internet Research, Vol 23, Iss 5, p e26933 (2021)
As of March 2021, the SARS-CoV-2 virus has been responsible for over 115 million cases of COVID-19 worldwide, resulting in over 2.5 million deaths. As the virus spread exponentially, so did its media coverage, resulting in a proliferation of conflict
Externí odkaz:
https://doaj.org/article/63f94a5128ba45bd93e96fead582d867
Autor:
Rai, Sunny, Zaveri, Khushang Jilesh, Havaldar, Shreya, Nema, Soumna, Ungar, Lyle, Guntuku, Sharath Chandra
Social emotions such as shame and pride reflect social sanctions or approvals in society. In this paper, we examine how expressions of shame and pride vary across cultures and harness them to extract unspoken normative expectations across cultures. W
Externí odkaz:
http://arxiv.org/abs/2402.11333
Autor:
Andy, Anietie U, Guntuku, Sharath C, Adusumalli, Srinath, Asch, David A, Groeneveld, Peter W, Ungar, Lyle H, Merchant, Raina M
Publikováno v:
JMIR Cardio, Vol 5, Iss 1, p e24473 (2021)
BackgroundCurrent atherosclerotic cardiovascular disease (ASCVD) predictive models have limitations; thus, efforts are underway to improve the discriminatory power of ASCVD models. ObjectiveWe sought to evaluate the discriminatory power of social me
Externí odkaz:
https://doaj.org/article/307e5bfe4cb844f2bae42f2180ff0c97