no code implementations • 15 Mar 2024 • Chaoqun Liu, Wenxuan Zhang, Yiran Zhao, Anh Tuan Luu, Lidong Bing
We find that even though translation into English can help improve the performance of multilingual NLP tasks for English-centric LLMs, it may not be optimal for all scenarios.
1 code implementation • 2 Mar 2024 • Yiran Zhao, Wenyue Zheng, Tianle Cai, Xuan Long Do, Kenji Kawaguchi, Anirudh Goyal, Michael Shieh
Safety of Large Language Models (LLMs) has become a central issue given their rapid progress and wide applications.
1 code implementation • 29 Feb 2024 • Yiran Zhao, Wenxuan Zhang, Huiming Wang, Kenji Kawaguchi, Lidong Bing
In this paper, we acknowledge the mutual reliance between task ability and language ability and direct our attention toward the gap between the target language and the source language on tasks.
no code implementations • 29 Feb 2024 • Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, Lidong Bing
We introduce a framework that depicts LLMs' processing of multilingual inputs: In the first several layers, LLMs understand the question, converting multilingual inputs into English to facilitate the task-solving phase.
no code implementations • 5 Dec 2023 • Xuan Long Do, Yiran Zhao, Hannah Brown, Yuxi Xie, James Xu Zhao, Nancy F. Chen, Kenji Kawaguchi, Michael Qizhe Xie, Junxian He
We propose a new method, Adversarial In-Context Learning (adv-ICL), to optimize prompt for in-context learning (ICL) by employing one LLM as a generator, another as a discriminator, and a third as a prompt modifier.
1 code implementation • NeurIPS 2023 • Shiqi Chen, Yiran Zhao, Jinghan Zhang, I-Chun Chern, Siyang Gao, PengFei Liu, Junxian He
In this benchmark, we collect responses generated from LLMs and annotate factuality labels in a fine-grained manner.
no code implementations • NeurIPS 2023 • Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, Qizhe Xie
Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness.
no code implementations • 2 Nov 2020 • Shuochao Yao, Yifan Hao, Yiran Zhao, Huajie Shao, Dongxin Liu, Shengzhong Liu, Tianshi Wang, Jinyang Li, Tarek Abdelzaher
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of local embedded devices that are themselves unable to support extensive computations.
1 code implementation • 21 Feb 2019 • Shuochao Yao, Ailing Piao, Wenjun Jiang, Yiran Zhao, Huajie Shao, Shengzhong Liu, Dongxin Liu, Jinyang Li, Tianshi Wang, Shaohan Hu, Lu Su, Jiawei Han, Tarek Abdelzaher
IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain.
no code implementations • 19 Sep 2018 • Shuochao Yao, Yiran Zhao, Huajie Shao, Shengzhong Liu, Dongxin Liu, Lu Su, Tarek Abdelzaher
We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time.
no code implementations • 9 Sep 2017 • Shuochao Yao, Yiran Zhao, Huajie Shao, Aston Zhang, Chao Zhang, Shen Li, Tarek Abdelzaher
Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ubiquitous applications.
1 code implementation • 5 Jun 2017 • Shuochao Yao, Yiran Zhao, Aston Zhang, Lu Su, Tarek Abdelzaher
It is thus able to shorten execution time by 71. 4% to 94. 5%, and decrease energy consumption by 72. 2% to 95. 7%.
1 code implementation • 7 Nov 2016 • Shuochao Yao, Shaohan Hu, Yiran Zhao, Aston Zhang, Tarek Abdelzaher
For many mobile applications, it is hard to find a distribution that exactly describes the noise in practice.