DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

Autor: Gema, Aryo Pradipta, Jin, Chen, Abdulaal, Ahmed, Diethe, Tom, Teare, Philip, Alex, Beatrice, Minervini, Pasquale, Saseendran, Amrutha

Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads within th

Externí odkaz: http://arxiv.org/abs/2410.18860

An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning

Autor: Jin, Chen, Tanno, Ryutaro, Saseendran, Amrutha, Diethe, Tom, Teare, Philip

Textural Inversion, a prompt learning method, learns a singular text embedding for a new "word" to represent image style and appearance, allowing it to be integrated into natural language sentences to generate novel synthesised images. However, ident

Externí odkaz: http://arxiv.org/abs/2310.12274

Improved clinical data imputation via classical and quantum determinantal point processes

Autor: Kazdaghli, Skander, Kerenidis, Iordanis, Kieckbusch, Jens, Teare, Philip

Imputing data is a critical issue for machine learning practitioners, including in the life sciences domain, where missing clinical data is a typical situation and the reliability of the imputation is of great importance. Currently, there is no canon

Externí odkaz: http://arxiv.org/abs/2303.17893

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans

Autor: Roberts, Michael, Driggs, Derek, Thorpe, Matthew, Gilbey, Julian, Yeung, Michael, Ursprung, Stephan, Aviles-Rivero, Angelica I., Etmann, Christian, McCague, Cathal, Beer, Lucian, Weir-McCall, Jonathan R., Teng, Zhongzhao, Gkrania-Klotsas, Effrossyni, Ruggiero, Alessandro, Korhonen, Anna, Jefferson, Emily, Ako, Emmanuel, Langs, Georg, Gozaliasl, Ghassem, Yang, Guang, Prosch, Helmut, Preller, Jacobus, Stanczuk, Jan, Tang, Jing, Hofmanninger, Johannes, Babar, Judith, Sánchez, Lorena Escudero, Thillai, Muhunthan, Gonzalez, Paula Martin, Teare, Philip, Zhu, Xiao Xiang, Patel, Mishal, Cafolla, Conor, Azadbakht, Hojjat, Jacob, Joseph, Lowe, Josh, Zhang, Kang, Bradley, Kyle, Wassin, Marcel, Holzer, Markus, Ji, Kangyu, Ortet, Maria Delgado, Ai, Tao, Walton, Nicholas, Lio, Pietro, Stranks, Samuel, Shadbahr, Tolou, Lin, Weizhe, Zha, Yunfei, Niu, Zhangming, Rudd, James H. F., Sala, Evis, Schönlieb, Carola-Bibiane

Publikováno v: Roberts, M, Driggs, D, Thorpe, M, Gilbey, J, Yeung, M, Ursprung, S, Aviles-Rivero, A, Etmann, C, McCague, C, Beer, L, Weir-McCall, J, Teng, Z, Gkrania-Klotsas, E, AIX-COVNET, Rudd, J, Sala, E & Schoenlieb, C-B 2021, ' Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans ', Nature Machine Intelligence, vol. 3, pp. 199-217 . https://doi.org/10.1038/s42256-021-00307-0

Machine learning methods offer great promise for fast and accurate detection and prognostication of COVID-19 from standard-of-care chest radiographs (CXR) and computed tomography (CT) images. Many articles have been published in 2020 describing new m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6203f7e866d10f75cc7e536c8041e1e0
http://hdl.handle.net/10138/329624