Zobrazeno 1 - 10
of 2 065
pro vyhledávání: '"Šimko, P."'
Autor:
Cegin, Jan, Pecher, Branislav, Simko, Jakub, Srba, Ivan, Bielikova, Maria, Brusilovsky, Peter
The generative large language models (LLMs) are increasingly used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for classifier fine-tuning. Existing works on augmentation leverage the few-shot scena
Externí odkaz:
http://arxiv.org/abs/2410.10756
The generative large language models (LLMs) are increasingly being used for data augmentation tasks, where text samples are LLM-paraphrased and then used for classifier fine-tuning. However, a research that would confirm a clear cost-benefit advantag
Externí odkaz:
http://arxiv.org/abs/2408.16502
Most US school districts draw geographic "attendance zones" to assign children to schools based on their home address, a process that can replicate existing neighborhood racial/ethnic and socioeconomic status (SES) segregation in schools. Redrawing b
Externí odkaz:
http://arxiv.org/abs/2408.12572
Autor:
Hrckova, Andrea, Renoux, Jennifer, Calasanz, Rafael Tolosana, Chuda, Daniela, Tamajka, Martin, Simko, Jakub
With the goal of uncovering the challenges faced by European AI students during their research endeavors, we surveyed 28 AI doctoral candidates from 13 European countries. The outcomes underscore challenges in three key areas: (1) the findability and
Externí odkaz:
http://arxiv.org/abs/2408.06847
Autor:
McCartan, Cory, Kenny, Christopher T., Simko, Tyler, Ebowe, Emma, Zhao, Michael Y., Imai, Kosuke
Political actors frequently manipulate redistricting plans to gain electoral advantages, a process commonly known as gerrymandering. To address this problem, several states have implemented institutional reforms including the establishment of map-dra
Externí odkaz:
http://arxiv.org/abs/2407.11336
The dissemination of false information on online platforms presents a serious societal challenge. While manual fact-checking remains crucial, Large Language Models (LLMs) offer promising opportunities to support fact-checkers with their vast knowledg
Externí odkaz:
http://arxiv.org/abs/2407.02351
Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination of parame
Externí odkaz:
http://arxiv.org/abs/2407.02317
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2024
While fine-tuning of pre-trained language models generally helps to overcome the lack of labelled training samples, it also displays model performance instability. This instability mainly originates from randomness in initialisation or data shuffling
Externí odkaz:
http://arxiv.org/abs/2406.12471
Autor:
Ciangottini, D., Forti, A., Heinrich, L., Skidmore, N., Alpigiani, C., Aly, M., Benjamin, D., Bockelman, B., Bryant, L., Catmore, J., D'Alfonso, M., Peris, A. Delgado, Doglioni, C., Duckeck, G., Elmer, P., Eschle, J., Feickert, M., Frost, J., Gardner, R., Garonne, V., Giffels, M., Gooding, J., Gramstad, E., Gray, L., Hegner, B., Held, A., Hernández, J., Holzman, B., Hu, F., Jashal, B. K., Kondratyev, D., Kourlitis, E., Kreczko, L., Krommydas, I., Kuhr, T., Lancon, E., Lange, C., Lange, D., Lange, J., Lenzi, P., Linden, T., Outschoorn, V. Martinez, McKee, S., Molina, J. F., Neubauer, M., Novak, A., Osborne, I., Ould-Saada, F., Pages, A. P., Pedro, K., Yzquierdo, A. Perez-Calero, Piperov, S., Pivarski, J., Rodrigues, E., Sahoo, N., Sciaba, A., Schulz, M., Sexton-Kennedy, L., Shadura, O., Šimko, T., Smith, N., Spiga, D., Stark, G., Stewart, G., Vukotic, I., Watts, G.
This white paper presents the current status of the R&D for Analysis Facilities (AFs) and attempts to summarize the views on the future direction of these facilities. These views have been collected through the High Energy Physics (HEP) Software Foun
Externí odkaz:
http://arxiv.org/abs/2404.02100
Autor:
Donadoni, Marco, Feickert, Matthew, Heinrich, Lukas, Liu, Yang, Mečionis, Audrius, Moisieienkov, Vladyslav, Šimko, Tibor, Stark, Giordon, García, Marco Vidal
In this paper we describe the development of a streamlined framework for large-scale ATLAS pMSSM reinterpretations of LHC Run-2 analyses using containerised computational workflows. The project is looking to assess the global coverage of BSM physics
Externí odkaz:
http://arxiv.org/abs/2403.03494