Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Tan, Weiting"'
Reinforcement Learning from Human Feedback (RLHF) involves training policy models (PMs) and reward models (RMs) to align language models with human preferences. Instead of focusing solely on PMs and RMs independently, we propose to examine their inte
Externí odkaz:
http://arxiv.org/abs/2406.07971
Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and offer faster i
Externí odkaz:
http://arxiv.org/abs/2405.13274
Autor:
Tan, Weiting, Chen, Yunmo, Chen, Tongfei, Qin, Guanghui, Xu, Haoran, Zhang, Heidi C., Van Durme, Benjamin, Koehn, Philipp
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representa
Externí odkaz:
http://arxiv.org/abs/2402.01172
Autor:
Shen, Lingfeng, Tan, Weiting, Chen, Sihao, Chen, Yunmo, Zhang, Jingyu, Xu, Haoran, Zheng, Boyuan, Koehn, Philipp, Khashabi, Daniel
As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by LLMs across d
Externí odkaz:
http://arxiv.org/abs/2401.13136
Autor:
Xu, Haoran, Sharaf, Amr, Chen, Yunmo, Tan, Weiting, Shen, Lingfeng, Van Durme, Benjamin, Murray, Kenton, Kim, Young Jin
Moderate-sized large language models (LLMs) -- those with 7B or 13B parameters -- exhibit promising machine translation (MT) performance. However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the performance of
Externí odkaz:
http://arxiv.org/abs/2401.08417
Neural finite-state transducers (NFSTs) form an expressive family of neurosymbolic sequence transduction models. An NFST models each string pair as having been generated by a latent path in a finite-state transducer. As they are deep generative model
Externí odkaz:
http://arxiv.org/abs/2312.13614
Autor:
Tan, Weiting, Xu, Haoran, Shen, Lingfeng, Li, Shuyue Stella, Murray, Kenton, Koehn, Philipp, Van Durme, Benjamin, Chen, Yunmo
Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations are relative
Externí odkaz:
http://arxiv.org/abs/2311.02310
Autor:
Xu, Haoran, Tan, Weiting, Li, Shuyue Stella, Chen, Yunmo, Van Durme, Benjamin, Koehn, Philipp, Murray, Kenton
Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation. This approach bears similarity to Mixture-of-Experts (MoE) because it does not inflate FLOPs. However, the scalability of this a
Externí odkaz:
http://arxiv.org/abs/2305.13993
With growing capabilities of large language models, prompting them has become the dominant way to access them. This has motivated the development of strategies for automatically selecting effective language prompts. In this paper, we introduce prompt
Externí odkaz:
http://arxiv.org/abs/2305.10713
Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive learning into
Externí odkaz:
http://arxiv.org/abs/2210.05033