Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ture, Ferhan"'
LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs, but we have been unable to find work that evaluates LLM stability as the main objective. In our study of 6 deterministically configured LLMs across 8
Externí odkaz:
http://arxiv.org/abs/2408.04667
Autor:
Tang, Raphael, Zhang, Xinyu, Xu, Lixinyu, Lu, Yao, Li, Wenyan, Stenetorp, Pontus, Lin, Jimmy, Ture, Ferhan
Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose W1KP, a human
Externí odkaz:
http://arxiv.org/abs/2406.08482
Customer service is how companies interface with their customers. It can contribute heavily towards the overall customer satisfaction. However, high-quality service can become expensive, creating an incentive to make it as cost efficient as possible
Externí odkaz:
http://arxiv.org/abs/2405.00801
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
Large language models (LLMs) exhibit positional bias in how they use context, which especially complicates listwise ranking. To address this, we propose permutation self-consistency, a form of self-consistency over ranking list outputs of black-box L
Externí odkaz:
http://arxiv.org/abs/2310.07712
Autor:
Tang, Raphael, Kumar, Karun, Yang, Gefei, Pandey, Akshat, Mao, Yajie, Belyaev, Vladislav, Emmadi, Madhuri, Murray, Craig, Ture, Ferhan, Lin, Jimmy
End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes commercialization
Externí odkaz:
http://arxiv.org/abs/2211.11740
Autor:
Tang, Raphael, Liu, Linqing, Pandey, Akshat, Jiang, Zhiying, Yang, Gefei, Kumar, Karun, Stenetorp, Pontus, Lin, Jimmy, Ture, Ferhan
Large-scale diffusion neural networks represent a substantial milestone in text-to-image generation, but they remain poorly understood, lacking interpretability analyses. In this paper, we perform a text-image attribution analysis on Stable Diffusion
Externí odkaz:
http://arxiv.org/abs/2210.04885
Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR) in the cloud. ASR systems require significant computational resources in training and for
Externí odkaz:
http://arxiv.org/abs/1812.07754
Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have only been applied to standard ad hoc retrieval tasks over web pages and newswire documents. This paper proposes MP-HCNN (Multi-Perspe
Externí odkaz:
http://arxiv.org/abs/1805.08159
Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams
Autor:
Rao, Jinfeng, He, Hua, Zhang, Haotian, Ture, Ferhan, Sequiera, Royal, Mohammed, Salman, Lin, Jimmy
Time is an important relevance signal when searching streams of social media posts. The distribution of document timestamps from the results of an initial query can be leveraged to infer the distribution of relevant documents, which can then be used
Externí odkaz:
http://arxiv.org/abs/1707.07792
We tackle the novel problem of navigational voice queries posed against an entertainment system, where viewers interact with a voice-enabled remote controller to specify the program to watch. This is a difficult problem for several reasons: such quer
Externí odkaz:
http://arxiv.org/abs/1705.04892