Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Yasunaga, Michihiro"'
Autor:
Wu, Shirley, Zhao, Shiyu, Huang, Qian, Huang, Kexin, Yasunaga, Michihiro, Cao, Kaidi, Ioannidis, Vassilis N., Subbian, Karthik, Leskovec, Jure, Zou, James
Large language model (LLM) agents have demonstrated impressive capability in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developing the prompting techniques that make LLM agents able to effectively use
Externí odkaz:
http://arxiv.org/abs/2406.11200
In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressiv
Externí odkaz:
http://arxiv.org/abs/2405.14831
Autor:
Wu, Shirley, Zhao, Shiyu, Yasunaga, Michihiro, Huang, Kexin, Cao, Kaidi, Huang, Qian, Ioannidis, Vassilis N., Subbian, Karthik, Zou, James, Leskovec, Jure
Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity rela
Externí odkaz:
http://arxiv.org/abs/2404.13207
Autor:
Bolton, Elliot, Venigalla, Abhinav, Yasunaga, Michihiro, Hall, David, Xiong, Betty, Lee, Tony, Daneshjou, Roxana, Frankle, Jonathan, Liang, Percy, Carbin, Michael, Manning, Christopher D.
Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks. However, these models have hundreds of billions of parameters, are computationally expensive to run, require users to send their i
Externí odkaz:
http://arxiv.org/abs/2403.18421
Autor:
Lee, Tony, Yasunaga, Michihiro, Meng, Chenlin, Mai, Yifan, Park, Joon Sung, Gupta, Agrim, Zhang, Yunzhi, Narayanan, Deepak, Teufel, Hannah Benita, Bellagente, Marco, Kang, Minguk, Park, Taesung, Leskovec, Jure, Zhu, Jun-Yan, Fei-Fei, Li, Wu, Jiajun, Ermon, Stefano, Liang, Percy
The stunning qualitative improvement of recent text-to-image models has led to their widespread attention and adoption. However, we lack a comprehensive quantitative understanding of their capabilities and risks. To fill this gap, we introduce a new
Externí odkaz:
http://arxiv.org/abs/2311.04287
Autor:
Yasunaga, Michihiro, Chen, Xinyun, Li, Yujia, Pasupat, Panupong, Leskovec, Jure, Liang, Percy, Chi, Ed H., Zhou, Denny
Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks, but typically needs labeled exemplars of the reasoning process. In this work, we introduce a new prompting approach, analogical prompting
Externí odkaz:
http://arxiv.org/abs/2310.01714
Autor:
Moor, Michael, Huang, Qian, Wu, Shirley, Yasunaga, Michihiro, Zakka, Cyril, Dalmia, Yash, Reis, Eduardo Pontes, Rajpurkar, Pranav, Leskovec, Jure
Medicine, by its nature, is a multifaceted domain that requires the synthesis of information across various modalities. Medical generative vision-language models (VLMs) make a first step in this direction and promise many exciting clinical applicatio
Externí odkaz:
http://arxiv.org/abs/2307.15189
Autor:
Zhang, Yuhui, Yasunaga, Michihiro, Zhou, Zhengping, HaoChen, Jeff Z., Zou, James, Liang, Percy, Yeung, Serena
Language models have been shown to exhibit positive scaling, where performance improves as models are scaled up in terms of size, compute, or data. In this work, we introduce NeQA, a dataset consisting of questions with negation in which language mod
Externí odkaz:
http://arxiv.org/abs/2305.17311
Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision of medical
Externí odkaz:
http://arxiv.org/abs/2302.09155
Spurred by advancements in scale, large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot -- i.e., without adaptation on downstream data. Recently, the debut of ChatGPT has
Externí odkaz:
http://arxiv.org/abs/2302.06476