Alert button
Picture for Dongdong Zhang

Dongdong Zhang

Alert button

Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

Feb 26, 2024
Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen

Viaarxiv icon

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Feb 20, 2024
Haoran Li, Qingxiu Dong, Zhengyang Tang, Chaojun Wang, Xingxing Zhang, Haoyang Huang, Shaohan Huang, Xiaolong Huang, Zeqiang Huang, Dongdong Zhang, Yuxian Gu, Xin Cheng, Xun Wang, Si-Qing Chen, Li Dong, Wei Lu, Zhifang Sui, Benyou Wang, Wai Lam, Furu Wei

Viaarxiv icon

Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing

May 24, 2023
Tianyi Tang, Hongyuan Lu, Yuchen Eleanor Jiang, Haoyang Huang, Dongdong Zhang, Wayne Xin Zhao, Furu Wei

Figure 1 for Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing
Figure 2 for Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing
Figure 3 for Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing
Figure 4 for Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing
Viaarxiv icon

One-stop Training of Multiple Capacity Models

May 24, 2023
Lan Jiang, Haoyang Huang, Dongdong Zhang, Rui Jiang, Furu Wei

Figure 1 for One-stop Training of Multiple Capacity Models
Figure 2 for One-stop Training of Multiple Capacity Models
Figure 3 for One-stop Training of Multiple Capacity Models
Figure 4 for One-stop Training of Multiple Capacity Models
Viaarxiv icon

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models

May 24, 2023
Hongyuan Lu, Haoyang Huang, Dongdong Zhang, Haoran Yang, Wai Lam, Furu Wei

Figure 1 for Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Figure 2 for Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Figure 3 for Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Figure 4 for Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Viaarxiv icon

Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation

May 23, 2023
Minwoo Lee, Hyukhun Koh, Kang-il Lee, Dongdong Zhang, Minsung Kim, Kyomin Jung

Figure 1 for Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Figure 2 for Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Figure 3 for Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Figure 4 for Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
Viaarxiv icon

Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus

May 18, 2023
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan, Ryan Cotterell

Figure 1 for Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
Figure 2 for Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
Figure 3 for Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
Figure 4 for Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
Viaarxiv icon

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation

May 18, 2023
Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang

Figure 1 for On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
Figure 2 for On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
Figure 3 for On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
Figure 4 for On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
Viaarxiv icon

Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting

May 11, 2023
Haoyang Huang, Tianyi Tang, Dongdong Zhang, Wayne Xin Zhao, Ting Song, Yan Xia, Furu Wei

Figure 1 for Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Figure 2 for Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Figure 3 for Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Figure 4 for Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Viaarxiv icon