Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Van Liemt, Erin"'
Autor:
Smart, Andrew, Hutchinson, Ben, Amugongo, Lameck Mbangula, Dikker, Suzanne, Zito, Alex, Ebinama, Amber, Wudiri, Zara, Wang, Ding, van Liemt, Erin, Sedoc, João, Olojo, Seyi, Uwakwe, Stanley, Wornyo, Edem, Schmer-Galunder, Sonja, Smith-Loud, Jamila
Publikováno v:
ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization, 2024
Large Language Models (LLMs) have rapidly increased in size and apparent capabilities in the last three years, but their training data is largely English text. There is growing interest in multilingual LLMs, and various efforts are striving for model
Externí odkaz:
http://arxiv.org/abs/2409.05247
AI applications across classification, fairness, and human interaction often implicitly require ontologies of social concepts. Constructing these well, especially when there are many relevant categories, is a controversial task but is crucial for ach
Externí odkaz:
http://arxiv.org/abs/2408.01455
Autor:
Chang, Tyler A., Tomanek, Katrin, Hoffmann, Jessica, Thain, Nithum, van Liemt, Erin, Meier-Hellstern, Kathleen, Dixon, Lucas
We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true answer and surface multiple perspectives. We frame this as retrieval augm
Externí odkaz:
http://arxiv.org/abs/2403.08904
Autor:
Quaye, Jessica, Parrish, Alicia, Inel, Oana, Rastogi, Charvi, Kirk, Hannah Rose, Kahng, Minsuk, van Liemt, Erin, Bartolo, Max, Tsang, Jess, White, Justin, Clement, Nathan, Mosquera, Rafael, Ciro, Juan, Reddi, Vijay Janapa, Aroyo, Lora
With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly adversarial'' promp
Externí odkaz:
http://arxiv.org/abs/2403.12075
Autor:
Smart, Andrew, Wang, Ding, Monk, Ellis, Díaz, Mark, Kasirzadeh, Atoosa, Van Liemt, Erin, Schmer-Galunder, Sonja
Data annotation remains the sine qua non of machine learning and AI. Recent empirical work on data annotation has begun to highlight the importance of rater diversity for fairness, model performance, and new lines of research have begun to examine th
Externí odkaz:
http://arxiv.org/abs/2402.06811