Zobrazeno 1 - 10
of 594
pro vyhledávání: '"Kim, Alex"'
We investigate whether an LLM can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determi
Externí odkaz:
http://arxiv.org/abs/2407.17866
As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as reference-free metrics
Externí odkaz:
http://arxiv.org/abs/2405.09935
Autor:
Soumagnac, Maayane T., Nugent, Peter, Knop, Robert A., Ho, Anna Y. Q., Hohensee, William, Awbrey, Autumn, Andersen, Alexis, Aldering, Greg, Ventura, Matan, Aguilar, Jessica N., Ahlen, Steven, Benzvi, Segev Y., Brooks, David, Brout, Dillon, Claybaugh, Todd, Davis, Tamara M., Dawson, Kyle, de la Macorra, Axel, Dey, Arjun, Dey, Biprateep, Doel, Peter, Douglass, Kelly A., Forero-Romero, Jaime E., Gaztanaga, Enrique, Gontcho, Satya Gontcho A, Graur, Or, Guy, Julien, Hahn, ChangHoon, Honscheid, Klaus, Howlett, Cullan, Kim, Alex G., Kisner, Theodore, Kremin, Anthony, Lambert, Andrew, Landriau, Martin, Lang, Dustin, Guillou, Laurent Le, Manera, Marc, Meisner, Aaron, Miquel, Ramon, Moustakas, John, Myers, Adam D., Nie, Jundan, Palmese, Antonella, Parkinson, David, Poppett, Claire, Prada, Francisco, Qin, Fei, Rezaie, Mehdi, Rossi, Graziano, Sanchez, Eusebio, Schlegel, David D., Schubnell, Michael, Silber, Joseph H., Tarle, Gregory, Weaver, Benjamin A., Zhou, Zhimin
We present the MOST Hosts survey (Multi-Object Spectroscopy of Transient Hosts). The survey is planned to run throughout the five years of operation of the Dark Energy Spectroscopic Instrument (DESI) and will generate a spectroscopic catalog of the h
Externí odkaz:
http://arxiv.org/abs/2405.03857
Autor:
Bag, Satadru, Huber, Simon, Suyu, Sherry H., Arendse, Nikki, Andika, Irham Taufik, Canameras, Raoul, Kim, Alex, Linder, Eric, Lodha, Kushal, Melo, Alejandra, More, Anupreeta, Schuldt, Stefan, Shafieloo, Arman
Strong-gravitationally lensed supernovae (LSNe) are promising probes for providing absolute distance measurements using gravitational lens time delays. Spatially unresolved LSNe offer an opportunity to enhance the sample size for precision cosmology.
Externí odkaz:
http://arxiv.org/abs/2404.15389
Autor:
Kim, Alex, Huang, Jia, Monarch, Rob, Kwac, Jerry, Kamath, Anikesh, Khurd, Parmeshwar, Thiyagarajan, Kailash, Gu, Goodman
Application developers advertise their Apps by creating product pages with App images, and bidding on search terms. It is then crucial for App images to be highly relevant with the search terms. Solutions to this problem require an image-text matchin
Externí odkaz:
http://arxiv.org/abs/2405.00029
Autor:
Kim, Alex, Yoon, Sangwon
Publikováno v:
Proceedings of the Third Workshop on Economics and Natural Language Processing, 2021, 26--36
This study performs BERT-based analysis, which is a representative contextualized language model, on corporate disclosure data to predict impending bankruptcies. Prior literature on bankruptcy prediction mainly focuses on developing more sophisticate
Externí odkaz:
http://arxiv.org/abs/2312.03194
Autor:
Kim, Alex, Yoon, Sangwon
Publikováno v:
Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media, 2022, 35--44
Kyle (1985) proposes two types of rumors: informed rumors which are based on some private information and uninformed rumors which are not based on any information (i.e. bluffing). Also, prior studies find that when people have credible source of info
Externí odkaz:
http://arxiv.org/abs/2312.03195
Autor:
Rubin, David, Aldering, Greg, Betoule, Marc, Fruchter, Andy, Huang, Xiaosheng, Kim, Alex G., Lidman, Chris, Linder, Eric, Perlmutter, Saul, Ruiz-Lapuente, Pilar, Suzuki, Nao
Type Ia supernovae (SNe Ia) were instrumental in establishing the acceleration of the universe's expansion. By virtue of their combination of distance reach, precision, and prevalence, they continue to provide key cosmological constraints, complement
Externí odkaz:
http://arxiv.org/abs/2311.12098
We explore the value of generative AI tools, such as ChatGPT, in helping investors uncover dimensions of corporate risk. We develop and validate firm-level measures of risk exposure to political, climate, and AI-related risks. Using the GPT 3.5 model
Externí odkaz:
http://arxiv.org/abs/2310.17721
Current large-scale astrophysical experiments produce unprecedented amounts of rich and diverse data. This creates a growing need for fast and flexible automated data inspection methods. Deep learning algorithms can capture and pick up subtle variati
Externí odkaz:
http://arxiv.org/abs/2308.00752