Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Tang, Liyan"'
Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of fact-checking are based on verifying each p
Externí odkaz:
http://arxiv.org/abs/2404.10774
Autor:
Tang, Liyan, Shalyminov, Igor, Wong, Amy Wing-mei, Burnsky, Jon, Vincent, Jake W., Yang, Yu'an, Singh, Siffi, Feng, Song, Song, Hwanjun, Su, Hang, Sun, Lijia, Zhang, Yi, Mansour, Saab, McKeown, Kathleen
Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text summarization dom
Externí odkaz:
http://arxiv.org/abs/2402.13249
A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less useful, whe
Externí odkaz:
http://arxiv.org/abs/2305.19339
Autor:
Tang, Liyan, Goyal, Tanya, Fabbri, Alexander R., Laban, Philippe, Xu, Jiacheng, Yavuz, Semih, Kryściński, Wojciech, Rousseau, Justin F., Durrett, Greg
The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems' outputs. However, the ever-evolving nature of su
Externí odkaz:
http://arxiv.org/abs/2205.12854
Autor:
Huang, Yao, Guan, Hua, Li, Chengbin, Zhang, Huaqing, Zhang, Baolin, Wang, Miao, Tang, Liyan, Shi, Tingyun, Gao, Kelin
For the first time, we experimentally determine the infrared magic wavelength for the $^{40}$Ca$^{+}$ $4s\, ^{2}\!S_{1/2} \rightarrow 3d\,^{2}\!D_{5/2}$ electric quadrupole transition by observation of the light shift canceling in $^{40}$Ca$^{+}$ opt
Externí odkaz:
http://arxiv.org/abs/2202.07828
Radiology report generation aims to produce computer-aided diagnoses to alleviate the workload of radiologists and has drawn increasing attention recently. However, previous deep learning methods tend to neglect the mutual influences between medical
Externí odkaz:
http://arxiv.org/abs/2201.03761
Radiology reports are unstructured and contain the imaging findings and corresponding diagnoses transcribed by radiologists which include clinical facts and negated and/or uncertain statements. Extracting pathologic findings and diagnoses from radiol
Externí odkaz:
http://arxiv.org/abs/2110.15426
Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report
Externí odkaz:
http://arxiv.org/abs/2110.07686
Autor:
Han, Yan, Chen, Chongyan, Tang, Liyan, Lin, Mingquan, Jaiswal, Ajay, Wang, Song, Tewfik, Ahmed, Shih, George, Ding, Ying, Peng, Yifan
Chest X-ray becomes one of the most common medical diagnoses due to its noninvasiveness. The number of chest X-ray images has skyrocketed, but reading chest X-rays still have been manually performed by radiologists, which creates huge burnouts and de
Externí odkaz:
http://arxiv.org/abs/2011.12506
Autor:
Wang, Song, Tang, Liyan, Majety, Akash, Rousseau, Justin F., Shih, George, Ding, Ying, Peng, Yifan
Publikováno v:
In Journal of Biomedical Informatics August 2022 132
