Zobrazeno 1 - 10
of 143
pro vyhledávání: '"O'BRIEN, KYLE"'
Autor:
O'Brien, Kyle, Majercak, David, Fernandes, Xavier, Edgar, Richard, Chen, Jingya, Nori, Harsha, Carignan, Dean, Horvitz, Eric, Poursabzi-Sangde, Forough
Responsible practices for deploying language models include guiding models to recognize and refuse answering prompts that are considered unsafe, while complying with safe prompts. Achieving such behavior typically requires updating model weights, whi
Externí odkaz:
http://arxiv.org/abs/2411.11296
Autor:
Kolbeinsson, Arinbjorn, O'Brien, Kyle, Huang, Tianjin, Gao, Shanghua, Liu, Shiwei, Schwarz, Jonathan Richard, Vaidya, Anurag, Mahmood, Faisal, Zitnik, Marinka, Chen, Tianlong, Hartvigsen, Thomas
Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing in
Externí odkaz:
http://arxiv.org/abs/2407.06483
Autor:
Prashanth, USVSN Sai, Deng, Alvin, O'Brien, Kyle, S V, Jyothir, Khan, Mohammad Aflah, Borkar, Jaydeep, Choquette-Choo, Christopher A., Fuehne, Jacob Ray, Biderman, Stella, Ke, Tracy, Lee, Katherine, Saphra, Naomi
Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the mo
Externí odkaz:
http://arxiv.org/abs/2406.17746
Autor:
O'Brien, Kyle, Ng, Nathan, Puri, Isha, Mendez, Jorge, Palangi, Hamid, Kim, Yoon, Ghassemi, Marzyeh, Hartvigsen, Thomas
Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model is effecti
Externí odkaz:
http://arxiv.org/abs/2402.08225
Autor:
Biderman, Stella, Schoelkopf, Hailey, Anthony, Quentin, Bradley, Herbie, O'Brien, Kyle, Hallahan, Eric, Khan, Mohammad Aflah, Purohit, Shivanshu, Prashanth, USVSN Sai, Raff, Edward, Skowron, Aviya, Sutawika, Lintang, van der Wal, Oskar
How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \textit{Pythia}, a suite of 16 LLMs all trained on public data seen in the exact
Externí odkaz:
http://arxiv.org/abs/2304.01373
Autor:
O'BRIEN, KYLE (AUTHOR), PHARMS, GABRIELLE NICOLE (AUTHOR), DANIELS, COLIN (AUTHOR), OSTWAL, TRISHLA (AUTHOR), FLEMING, JAMESON (AUTHOR), KIEFER, BRITTANEY (AUTHOR)
Publikováno v:
Adweek. Aug2024, Vol. 64 Issue 7, p26-35. 9p. 16 Color Photographs, 4 Black and White Photographs.
Publikováno v:
Adweek. May2024, Vol. 64 Issue 5, p18-39. 18p. 10 Color Photographs.
Autor:
Bernstein, Garrett, O'Brien, Kyle
Publikováno v:
Bernstein, G. and O'Brien, K. 'Stochastic Agent-Based Simulations of Social Networks.' Proceedings of 46th Annual Simulation Symposium, San Diego, 7-10 April 2013. 33-40. Print
The rapidly growing field of network analytics requires data sets for use in evaluation. Real world data often lack truth and simulated data lack narrative fidelity or statistical generality. This paper presents a novel, mixed-membership, agentbased
Externí odkaz:
http://arxiv.org/abs/1309.1747
Publikováno v:
In Child and Adolescent Psychiatric Clinics of North America April 2019 28(2):157-169
Autor:
Ferris, Cheyenne1,2 (AUTHOR) Cheyenne.ferris@klingberg.com, O'Brien, Kyle2 (AUTHOR)
Publikováno v:
Journal of Traumatic Stress. Oct2022, Vol. 35 Issue 5, p1305-1317. 13p. 1 Diagram, 1 Chart.