Zobrazeno 1 - 10
of 3 069
pro vyhledávání: '"SHEN, Hua"'
As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems align with t
Externí odkaz:
http://arxiv.org/abs/2409.09586
Prompting LLMs for complex tasks (e.g., building a trip advisor chatbot) needs humans to clearly articulate customized requirements (e.g., "start the response with a tl;dr"). However, existing prompt engineering instructions often lack focused traini
Externí odkaz:
http://arxiv.org/abs/2409.08775
Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue
Autor:
Ivey, Jonathan, Kumar, Shivani, Liu, Jiayu, Shen, Hua, Rakshit, Sushrita, Raju, Rohan, Zhang, Haotian, Ananthasubramaniam, Aparna, Kim, Junghwan, Yi, Bowen, Wright, Dustin, Israeli, Abraham, Møller, Anders Giovanni, Zhang, Lechen, Jurgens, David
Studying and building datasets for dialogue tasks is both expensive and time-consuming due to the need to recruit, train, and collect data from study participants. In response, much recent work has sought to use large language models (LLMs) to simula
Externí odkaz:
http://arxiv.org/abs/2409.08330
Autor:
Chang, Kai-Wei, Wu, Haibin, Wang, Yu-Kai, Wu, Yuan-Kuei, Shen, Hua, Tseng, Wei-Cheng, Kang, Iu-thing, Li, Shang-Wen, Lee, Hung-yi
Publikováno v:
in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 3730-3744, 2024
Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both sto
Externí odkaz:
http://arxiv.org/abs/2408.13040
In Explainable AI (XAI), counterfactual explanations (CEs) are a well-studied method to communicate feature relevance through contrastive reasoning of "what if" to explain AI models' predictions. However, they only focus on important (i.e., relevant)
Externí odkaz:
http://arxiv.org/abs/2408.10528
Autor:
Shen, Hua, Knearem, Tiffany, Ghosh, Reshmi, Alkiek, Kenan, Krishna, Kundan, Liu, Yachuan, Ma, Ziqiao, Petridis, Savvas, Peng, Yi-Hao, Qiwei, Li, Rakshit, Sushrita, Si, Chenglei, Xie, Yutong, Bigham, Jeffrey P., Bentley, Frank, Chai, Joyce, Lipton, Zachary, Mei, Qiaozhu, Mihalcea, Rada, Terry, Michael, Yang, Diyi, Morris, Meredith Ringel, Resnick, Paul, Jurgens, David
Recent advancements in general-purpose AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. However, the lack of clar
Externí odkaz:
http://arxiv.org/abs/2406.09264
Autor:
Montenegro-Garreaud, Ximena, Hansen, Adam W., Khayat, Michael M., Chander, Varuna, Grochowski, Christopher M., Jiang, Yunyun, Li, He, Mitani, Tadahiro, Kessler, Elena, Jayaseelan, Joy, Shen, Hua, Gezdirici, Alper, Pehlivan, Davut, Meng, Qingchang, Rosenfeld, Jill A., Jhangiani, Shalini N., Madan-Khetarpal, Suneeta, Scott, Daryl A., Abarca-Barriga, Hugo, Trubnykova, Milana, Gingras, Marie Claude, Muzny, Donna M., Posey, Jennifer E., Liu, Pengfei, Lupski, James R., Gibbs, Richard A.
Publikováno v:
Universidad Peruana de Ciencias Aplicadas (UPC)Repositorio Academico - UPCHuman Mutation.
KIF1A is a molecular motor for membrane-bound cargo important to the development and survival of sensory neurons. KIF1A dysfunction has been associated with several Mendelian disorders with a spectrum of overlapping phenotypes, ranging from spastic p
Externí odkaz:
http://hdl.handle.net/10757/655505
Autor:
Lee, Mina, Gero, Katy Ilonka, Chung, John Joon Young, Shum, Simon Buckingham, Raheja, Vipul, Shen, Hua, Venugopalan, Subhashini, Wambsganss, Thiemo, Zhou, David, Alghamdi, Emad A., August, Tal, Bhat, Avinash, Choksi, Madiha Zahrah, Dutta, Senjuti, Guo, Jin L. C., Hoque, Md Naimul, Kim, Yewon, Knight, Simon, Neshaei, Seyed Parsa, Sergeyuk, Agnia, Shibani, Antonette, Shrivastava, Disha, Shroff, Lila, Stark, Jessi, Sterman, Sarah, Wang, Sitong, Bosselut, Antoine, Buschek, Daniel, Chang, Joseph Chee, Chen, Sherol, Kreminski, Max, Park, Joonsuk, Pea, Roy, Rho, Eugenia H., Shen, Shannon Zejiang, Siangliulue, Pao
In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to
Externí odkaz:
http://arxiv.org/abs/2403.14117
Autor:
Gorlo, Nicolas, Bamert, Samuel, Cathomen, Rafael, Käppeli, Gabriel, Müller, Mario, Reinhart, Tim, Stadler, Henriette, Shen, Hua, Cuniato, Eugenio, Tognon, Marco, Siegwart, Roland
In challenging terrains, constructing structures such as antennas and cable-car masts often requires the use of helicopters to transport loads via ropes. The swinging of the load, exacerbated by wind, impairs positioning accuracy, therefore necessita
Externí odkaz:
http://arxiv.org/abs/2312.01988
Publikováno v:
AIED 2024, LNAI 14829, pp. 1-16
Large Language Models (LLMs) now excel at generative skills and can create content at impeccable speeds. However, they are imperfect and still make various mistakes. In a Computer Science education context, as these models are widely recognized as "A
Externí odkaz:
http://arxiv.org/abs/2310.05292