Baosong Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Baosong Yang has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
Pei Zhang
Lab Alibaba Group Inc
9 shared publicationsJun Xie
Lab Tongyi
8 shared publications- Derek Fai Wong
University of Macau
6 shared publications - Rui Wang
Shanghai Jiao Tong University
5 shared publications - Boxing Chen
Huawei Technologies Ltd., Montreal, Canada
4 shared publications - Dayiheng Liu
Qwen Team AI Institute 8x Efficiency Alibaba Group 3 UW-Madison 4 UIUC 5 Mila Quebec
4 shared publications
Latest Publications
- Open Access
CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While several cultural benchmarks exist to assess LLMs' cultural competence, current evaluations suffer from fragmented taxonomies, domain specificity, and heavy reliance on manual data annotation. To address these limitations, we introduce CultureSynth, a novel framework comprising (1) a comprehensive hierarchical multilingual cultural taxonomy covering 12 primary and 130 secondary topics, and (2) a Retrieval-Augmented Generation (RAG)-based methodology leveraging factual knowledge to synthesize culturally relevant question-answer pairs. The CultureSynth-7 synthetic benchmark contains 19,360 entries and 4,149 manually verified entries across 7 languages. Evaluation of 14 prevalent LLMs of different sizes reveals clear performance stratification led by ChatGPT-4o-Latest and Qwen2.5-72B-Instruct. The results demonstrate that a 3B-parameter threshold is necessary for achieving basic cultural competence, models display varying architectural biases in knowledge processing, and significant geographic disparities exist across models. We believe that CultureSynth offers a scalable framework for developing culturally aware AI systems while reducing reliance on manual annotation\footnote{Benchmark is available at https://github.com/Eyr3/CultureSynth.}.
Open AccessCultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While several cultural benchmarks exist to assess LLMs' cultural competence, current evaluations suffer from fragmented taxonomies, domain specificity, and heavy reliance on manual data annotation. To address these limitations, we introduce CultureSynth, a novel framework comprising (1) a comprehensive hierarchical multilingual cultural taxonomy covering 12 primary and 130 secondary topics, and (2) a Retrieval-Augmented Generation (RAG)-based methodology leveraging factual knowledge to synthesize culturally relevant question-answer pairs. The CultureSynth-7 synthetic benchmark contains 19,360 entries and 4,149 manually verified entries across 7 languages. Evaluation of 14 prevalent LLMs of different sizes reveals clear performance stratification led by ChatGPT-4o-Latest and Qwen2.5-72B-Instruct. The results demonstrate that a 3B-parameter threshold is necessary for achieving basic cultural competence, models display varying architectural biases in knowledge processing, and significant geographic disparities exist across models. We believe that CultureSynth offers a scalable framework for developing culturally aware AI systems while reducing reliance on manual annotation\footnote{Benchmark is available at https://github.com/Eyr3/CultureSynth.}.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10448-10467
CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan, Baosong Yang, Fei Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10448-10467
Open AccessCultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan, Baosong Yang, Fei Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27140-27154
Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training
Linjuan Wu, Hao-Ran Wei, Huan Lin, Tianhao Li, Baosong Yang, Fei Huang, Weiming Lu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27140-27154
Open AccessEnhancing LLM Language Adaption through Cross-lingual In-Context Pre-training
Linjuan Wu, Hao-Ran Wei, Huan Lin, Tianhao Li, Baosong Yang, Fei Huang, Weiming Lu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 23006-23023
From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction Tuning
Linjuan Wu, Hao-Ran Wei, Baosong Yang, Weiming Lu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 23006-23023
Open AccessFrom English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction Tuning
Linjuan Wu, Hao-Ran Wei, Baosong Yang, Weiming Lu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 23916-23934
Enhancing Machine Translation with Self-Supervised Preference Data
Haoxiang Sun, Ruize Gao, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 23916-23934
Open AccessEnhancing Machine Translation with Self-Supervised Preference Data
Haoxiang Sun, Ruize Gao, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models (LLMs) have demonstrated impressive general understanding and generation abilities, their potential in multi-domain MT is under-explored. We establish a comprehensive benchmark for multi-domain translation, featuring 25 German$\Leftrightarrow$English and 22 Chinese$\Leftrightarrow$English test sets respectively covering 15 domains. Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. This method inspires the LLM to perceive domain information from the source text, which then serves as a helpful hint to guide the translation process. Despite being trained on a small dataset of four domains, our CoT fine-tune approach achieves notable enhancements in translation accuracy and domain robustness than traditional fine-tuning, as evidenced by an average 1.53 BLEU score increase in over 20 German$\rightarrow$English distinct out-of-domain tests.
Open AccessLarge Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models (LLMs) have demonstrated impressive general understanding and generation abilities, their potential in multi-domain MT is under-explored. We establish a comprehensive benchmark for multi-domain translation, featuring 25 German$\Leftrightarrow$English and 22 Chinese$\Leftrightarrow$English test sets respectively covering 15 domains. Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. This method inspires the LLM to perceive domain information from the source text, which then serves as a helpful hint to guide the translation process. Despite being trained on a small dataset of four domains, our CoT fine-tune approach achieves notable enhancements in translation accuracy and domain robustness than traditional fine-tuning, as evidenced by an average 1.53 BLEU score increase in over 20 German$\rightarrow$English distinct out-of-domain tests.
- Open Access
- 1 March 2024
- Published by MIT Press in Computational Linguistics
- Vol. 50 (1) , 25-47
Rethinking the Exploitation of Monolingual Data for Low-Resource Neural Machine Translation
The utilization of monolingual data has been shown to be a promising strategy for addressing low-resource machine translation problems. Previous studies have demonstrated the effectiveness of techniques such as back-translation and self-supervised objectives, including masked language modeling, causal language modeling, and denoise autoencoding, in improving the performance of machine translation models. However, the manner in which these methods contribute to the success of machine translation tasks and how they can be effectively combined remains an under-researched area. In this study, we carry out a systematic investigation of the effects of these techniques on linguistic properties through the use of probing tasks, including source language comprehension, bilingual word alignment, and translation fluency. We further evaluate the impact of pre-training, back-translation, and multi-task learning on bitexts of varying sizes. Our findings inform the design of more effective pipelines for leveraging monolingual data in extremely low-resource and low-resource machine translation tasks. Experiment results show consistent performance gains in seven translation directions, which provide further support for our conclusions and understanding of the role of monolingual data in machine translation.
- 1 March 2024
- Published by MIT Press in Computational Linguistics
- Vol. 50 (1) , 25-47
Open AccessRethinking the Exploitation of Monolingual Data for Low-Resource Neural Machine Translation
The utilization of monolingual data has been shown to be a promising strategy for addressing low-resource machine translation problems. Previous studies have demonstrated the effectiveness of techniques such as back-translation and self-supervised objectives, including masked language modeling, causal language modeling, and denoise autoencoding, in improving the performance of machine translation models. However, the manner in which these methods contribute to the success of machine translation tasks and how they can be effectively combined remains an under-researched area. In this study, we carry out a systematic investigation of the effects of these techniques on linguistic properties through the use of probing tasks, including source language comprehension, bilingual word alignment, and translation fluency. We further evaluate the impact of pre-training, back-translation, and multi-task learning on bitexts of varying sizes. Our findings inform the design of more effective pipelines for leveraging monolingual data in extremely low-resource and low-resource machine translation tasks. Experiment results show consistent performance gains in seven translation directions, which provide further support for our conclusions and understanding of the role of monolingual data in machine translation.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 967-972
Final Submission of SJTULoveFiction to Literary Task
Haoxiang Sun, Tianxiang Hu, Ruize Gao, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the Ninth Conference on Machine Translation. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 967-972
Open AccessFinal Submission of SJTULoveFiction to Literary Task
Haoxiang Sun, Tianxiang Hu, Ruize Gao, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the Ninth Conference on Machine Translation. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5726-5746
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek F. Wong, Rui Wang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5726-5746
Open AccessLarge Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek F. Wong, Rui Wang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 943-948
SJTU System Description for the WMT24 Low-Resource Languages of Spain Task
Tianxiang Hu, Haoxiang Sun, Ruize Gao, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the Ninth Conference on Machine Translation. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 943-948
Open AccessSJTU System Description for the WMT24 Low-Resource Languages of Spain Task
Tianxiang Hu, Haoxiang Sun, Ruize Gao, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang. Proceedings of the Ninth Conference on Machine Translation. 2024.