Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Dejl, Adam"'
Autor:
Zhai, Xuehao, Jiang, Junqi, Dejl, Adam, Rago, Antonio, Guo, Fangce, Toni, Francesca, Sivakumar, Aruna
Urban land use inference is a critically important task that aids in city planning and policy-making. Recently, the increased use of sensor and location technologies has facilitated the collection of multi-modal mobility data, offering valuable insig
Externí odkaz:
http://arxiv.org/abs/2406.13724
Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has largely focused on locating entity-related (often single-token) facts i
Externí odkaz:
http://arxiv.org/abs/2406.10868
Autor:
Leofante, Francesco, Ayoobi, Hamed, Dejl, Adam, Freedman, Gabriel, Gorur, Deniz, Jiang, Junqi, Paulino-Passos, Guilherme, Rago, Antonio, Rapberger, Anna, Russo, Fabrizio, Yin, Xiang, Zhang, Dekai, Toni, Francesca
AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated decision-ma
Externí odkaz:
http://arxiv.org/abs/2405.10729
The diversity of knowledge encoded in large language models (LLMs) and their ability to apply this knowledge zero-shot in a range of settings makes them a promising candidate for use in decision-making. However, they are currently limited by their in
Externí odkaz:
http://arxiv.org/abs/2405.02079
Autor:
Wong, Anna, Ge, Shu, Oufattole, Nassim, Dejl, Adam, Su, Megan, Saeedi, Ardavan, Lehman, Li-wei H.
Sepsis is a life-threatening condition triggered by an extreme infection response. Our objective is to forecast sepsis patient outcomes using their medical history and treatments, while learning interpretable state representations to assess patients'
Externí odkaz:
http://arxiv.org/abs/2311.09566
Feature attribution methods are widely used to explain neural models by determining the influence of individual input features on the models' outputs. We propose a novel feature attribution method, CAFE (Conflict-Aware Feature-wise Explanations), tha
Externí odkaz:
http://arxiv.org/abs/2310.20363
RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction
Autor:
Khanna, Sameer, Dejl, Adam, Yoon, Kibo, Truong, Quoc Hung, Duong, Hanh, Saenz, Agustina, Rajpurkar, Pranav
We present RadGraph2, a novel dataset for extracting information from radiology reports that focuses on capturing changes in disease state and device placement over time. We introduce a hierarchical schema that organizes entities based on their relat
Externí odkaz:
http://arxiv.org/abs/2308.05046
Sum-product networks (SPNs) have recently emerged as a novel deep learning architecture enabling highly efficient probabilistic inference. Since their introduction, SPNs have been applied to a wide range of data modalities and extended to time-sequen
Externí odkaz:
http://arxiv.org/abs/2211.07052