Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Faiza, Khan"'
Autor:
Dige, Omkar, Singh, Diljot, Yau, Tsz Fung, Zhang, Qixuan, Bolandraftar, Borna, Zhu, Xiaodan, Khattak, Faiza Khan
Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs. Numerous approaches revolve around data pre-processing and fine-tuning of language models, tasks that can be both time-consuming and compu
Externí odkaz:
http://arxiv.org/abs/2406.13551
Modern large language models (LLMs) have a significant amount of world knowledge, which enables strong performance in commonsense reasoning and knowledge-intensive tasks when harnessed properly. The language model can also learn social biases, which
Externí odkaz:
http://arxiv.org/abs/2405.04756
Autor:
Kohankhaki, Farnaz, Emerson, D. B., Tian, Jacob-Junqi, Seyyed-Kalantari, Laleh, Khattak, Faiza Khan
Bias in large language models (LLMs) has many forms, from overt discrimination to implicit stereotypes. Counterfactual bias evaluation is a widely used approach to quantifying bias and often relies on template-based probes that explicitly state group
Externí odkaz:
http://arxiv.org/abs/2404.03471
Large language models (LLMs) are trained on vast, uncurated datasets that contain various forms of biases and language reinforcing harmful stereotypes that may be subsequently inherited by the models themselves. Therefore, it is essential to examine
Externí odkaz:
http://arxiv.org/abs/2308.00071
As the breadth and depth of language model applications continue to expand rapidly, it is increasingly important to build efficient frameworks for measuring and mitigating the learned or inherited social biases of these models. In this paper, we pres
Externí odkaz:
http://arxiv.org/abs/2307.10472
Autor:
Tian, Jacob-Junqi, Emerson, David, Miyandoab, Sevil Zanjani, Pandya, Deval, Seyyed-Kalantari, Laleh, Khattak, Faiza Khan
Prompting large language models has gained immense popularity in recent years due to the advantage of producing good results even without the need for labelled data. However, this requires prompt tuning to get optimal prompts that lead to better mode
Externí odkaz:
http://arxiv.org/abs/2306.04735
Autor:
Khattak, Faiza Khan, Subasri, Vallijah, Krishnan, Amrit, Dolatabadi, Elham, Pandya, Deval, Seyyed-Kalantari, Laleh, Rudzicz, Frank
Machine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in healthcare settings. This paper provides both a survey of work in this a
Externí odkaz:
http://arxiv.org/abs/2305.02474
Autor:
Obadinma, Stephen, Khattak, Faiza Khan, Wang, Shirley, Sidhom, Tania, Lau, Elaine, Robertson, Sean, Niu, Jingcheng, Au, Winnie, Munim, Alif, Bhaskar, Karthik Raja K., Wei, Bencheng, Ren, Iris, Muhammad, Waqar, Li, Erin, Ishola, Bukola, Wang, Michael, Tanner, Griffin, Shiah, Yu-Jia, Zhang, Sean X., Apponsah, Kwesi P., Patel, Kanishk, Narain, Jaswinder, Pandya, Deval, Zhu, Xiaodan, Rudzicz, Frank, Dolatabadi, Elham
Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natural Language Processing (NLP) technology. We combine expertise from acad
Externí odkaz:
http://arxiv.org/abs/2302.03222
Autor:
Mohsin Khan, Naima Khan, Shehla Noor, Ahtezaz Hussain, Hameed Ur Rahman, Sadia Irshad, Faiza Khan
Publikováno v:
Journal of Gandhara Medical and Dental Sciences, Vol 11, Iss 4 (2024)
OBJECTIVES The study aimed to determine the maternal morbidities in patients with placenta previa in a tertiary care hospital. Moreover, patients’ risk factors and outcomes will also be accessed as secondary outcomes. METHODOLOGY This prospec
Externí odkaz:
https://doaj.org/article/ba6f518b95e349f68ec8462fa2777e07
Autor:
Urooba Sehar, Summrina Kanwal, Nasser I. Allheeib, Sultan Almari, Faiza Khan, Kia Dashtipur, Mandar Gogate, Osama A. Khashan
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-16 (2023)
Abstract In the digital age, social media has emerged as a significant platform, generating a vast amount of raw data daily. This data reflects the opinions of individuals from diverse backgrounds, races, cultures, and age groups, spanning a wide ran
Externí odkaz:
https://doaj.org/article/e2322869c1d04a3ebc6043d0feb43894