Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Shen, Lingfeng"'
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:
Ye, Xiao, Wang, Andrew, Choi, Jacob, Lu, Yining, Sharma, Shreya, Shen, Lingfeng, Tiyyala, Vijay, Andrews, Nicholas, Khashabi, Daniel
Humans regularly engage in analogical thinking, relating personal experiences to current situations (X is analogous to Y because of Z). Analogical thinking allows humans to solve problems in creative ways, grasp difficult concepts, and articulate ide
Externí odkaz:
http://arxiv.org/abs/2402.12370
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
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
The emergence of In-Context Learning (ICL) in LLMs remains a remarkable phenomenon that is partially understood. To explain ICL, recent studies have created theoretical connections to Gradient Descent (GD). We ask, do such connections hold up in actu
Externí odkaz:
http://arxiv.org/abs/2310.08540
Autor:
Hou, Abe Bohan, Zhang, Jingyu, He, Tianxing, Wang, Yichen, Chuang, Yung-Sung, Wang, Hongwei, Shen, Lingfeng, Van Durme, Benjamin, Khashabi, Daniel, Tsvetkov, Yulia
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive hashing (LSH),
Externí odkaz:
http://arxiv.org/abs/2310.03991
Autor:
Shen, Lingfeng, Chen, Sihao, Song, Linfeng, Jin, Lifeng, Peng, Baolin, Mi, Haitao, Khashabi, Daniel, Yu, Dong
Standard practice within Reinforcement Learning from Human Feedback (RLHF) involves optimizing against a Reward Model (RM), which itself is trained to reflect human preferences for desirable generations. A notable subject that is understudied is the
Externí odkaz:
http://arxiv.org/abs/2309.16155
Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks. The recent breakthrough in sentence embedding is achieved by pre-trained language models (PLMs). Despite its success,
Externí odkaz:
http://arxiv.org/abs/2306.02247