Zobrazeno 1 - 10
of 8 234
pro vyhledávání: '"LEE, DANIEL"'
Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliterat
Externí odkaz:
http://arxiv.org/abs/2410.14057
Autor:
Lee, Daniel J., Heimersheim, Stefan
Sensitive directions experiments attempt to understand the computational features of Language Models (LMs) by measuring how much the next token prediction probabilities change by perturbing activations along specific directions. We extend the sensiti
Externí odkaz:
http://arxiv.org/abs/2410.12555
Autor:
Wang, Yifan, Stevens, David, Shah, Pranay, Jiang, Wenwen, Liu, Miao, Chen, Xu, Kuo, Robert, Li, Na, Gong, Boying, Lee, Daniel, Hu, Jiabo, Zhang, Ning, Kamma, Bob
The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality. We propose the Model-
Externí odkaz:
http://arxiv.org/abs/2409.10702
Autor:
Dixit, Tanay, Lee, Daniel, Fang, Sally, Harsha, Sai Sree, Sureshan, Anirudh, Maharaj, Akash, Li, Yunyao
Large Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to performance
Externí odkaz:
http://arxiv.org/abs/2409.03928
Autor:
Zhu, Zhengyuan, Lee, Daniel, Zhang, Hong, Harsha, Sai Sree, Feujio, Loic, Maharaj, Akash, Li, Yunyao
Recent advancements in retrieval-augmented generation (RAG) have demonstrated impressive performance in the question-answering (QA) task. However, most previous works predominantly focus on text-based answers. While some studies address multimodal da
Externí odkaz:
http://arxiv.org/abs/2408.08521
Autor:
Pradeep, Ronak, Lee, Daniel, Mousavi, Ali, Pound, Jeff, Sang, Yisi, Lin, Jimmy, Ilyas, Ihab, Potdar, Saloni, Arefiyan, Mostafa, Li, Yunyao
The rapid advancement of Large Language Models (LLMs) and conversational assistants necessitates dynamic, scalable, and configurable conversational datasets for training and evaluation. These datasets must accommodate diverse user interaction modes,
Externí odkaz:
http://arxiv.org/abs/2408.05948
We present a general class of machine learning algorithms called parametric matrix models. In contrast with most existing machine learning models that imitate the biology of neurons, parametric matrix models use matrix equations that emulate the phys
Externí odkaz:
http://arxiv.org/abs/2401.11694