Min Zhang
Research Subjects
Research Interests
Min Zhang has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
- Hao Yang
National University of Defense Technology
28 shared publications - Shimin Tao
Huawei
16 shared publications - Chang Su
Huawei China
15 shared publications - Xiaosong Qiao
Huawei Translation Services Center
12 shared publications - Yanqing Zhao
Huawei Translation Services Center
10 shared publications - Minghan Wang
Huawei Translation Service Center Beijing China
9 shared publications
Latest Publications
- 16 November 2025
- Published by Springer Nature
- p. 175-187
Improving LLM-Based Document-Level MT with Multi-Knowledge Fusion
- 16 November 2025
- Published by Springer Nature
- p. 175-187
Improving LLM-Based Document-Level MT with Multi-Knowledge Fusion
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1246-1254
Graph Alignment Using Seed-Oriented Subgraph Matching
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1246-1254
Open AccessGraph Alignment Using Seed-Oriented Subgraph Matching
- Open Access
Investigating Numerical Translation with Large Language Models
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their capacity for translating numbers has not been thoroughly explored. This study focuses on evaluating the reliability of LLM-based machine translation systems when handling numerical data. In order to systematically test the numerical translation capabilities of currently open source LLMs, we have constructed a numerical translation dataset between Chinese and English based on real business data, encompassing ten types of numerical translation. Experiments on the dataset indicate that errors in numerical translation are a common issue, with most open-source LLMs faltering when faced with our test scenarios. Especially when it comes to numerical types involving large units like ``million", ``billion", and "yi", even the latest llama3.1 8b model can have error rates as high as 20%. Finally, we introduce three potential strategies to mitigate the numerical mistranslations for large units.
Open AccessInvestigating Numerical Translation with Large Language Models
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their capacity for translating numbers has not been thoroughly explored. This study focuses on evaluating the reliability of LLM-based machine translation systems when handling numerical data. In order to systematically test the numerical translation capabilities of currently open source LLMs, we have constructed a numerical translation dataset between Chinese and English based on real business data, encompassing ten types of numerical translation. Experiments on the dataset indicate that errors in numerical translation are a common issue, with most open-source LLMs faltering when faced with our test scenarios. Especially when it comes to numerical types involving large units like ``million", ``billion", and "yi", even the latest llama3.1 8b model can have error rates as high as 20%. Finally, we introduce three potential strategies to mitigate the numerical mistranslations for large units.
- Open Access
"I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities
Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.
Open Access"I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities
Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.
- Open Access
LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
Recent advancements in integrating speech information into large language models (LLMs) have significantly improved automatic speech recognition (ASR) accuracy. However, existing methods often constrained by the capabilities of the speech encoders under varied acoustic conditions, such as accents. To address this, we propose LA-RAG, a novel Retrieval-Augmented Generation (RAG) paradigm for LLM-based ASR. LA-RAG leverages fine-grained token-level speech datastores and a speech-to-speech retrieval mechanism to enhance ASR accuracy via LLM in-context learning (ICL) capabilities. Experiments on Mandarin and various Chinese dialect datasets demonstrate significant improvements in ASR accuracy compared to existing methods, validating the effectiveness of our approach, especially in handling accent variations.
Open AccessLA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
Recent advancements in integrating speech information into large language models (LLMs) have significantly improved automatic speech recognition (ASR) accuracy. However, existing methods often constrained by the capabilities of the speech encoders under varied acoustic conditions, such as accents. To address this, we propose LA-RAG, a novel Retrieval-Augmented Generation (RAG) paradigm for LLM-based ASR. LA-RAG leverages fine-grained token-level speech datastores and a speech-to-speech retrieval mechanism to enhance ASR accuracy via LLM in-context learning (ICL) capabilities. Experiments on Mandarin and various Chinese dialect datasets demonstrate significant improvements in ASR accuracy compared to existing methods, validating the effectiveness of our approach, especially in handling accent variations.
- Open Access
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of high-quality instruction datasets is costly, leading to the adoption of automatic generation of instruction pairs by LLMs as a popular alternative. To ensure the high quality of LLM-generated instruction datasets, several approaches have been proposed. Nevertheless, existing methods either compromise dataset integrity by filtering a large proportion of samples, or are unsuitable for industrial applications. In this paper, instead of discarding low-quality samples, we propose CoachLM, a novel approach to enhance the quality of instruction datasets through automatic revisions on samples in the dataset. CoachLM is trained from the samples revised by human experts and significantly increases the proportion of high-quality samples in the dataset from 17.7% to 78.9%. The effectiveness of CoachLM is further assessed on various real-world instruction test sets. The results show that CoachLM improves the instruction-following capabilities of the instruction-tuned LLM by an average of 29.9%, which even surpasses larger LLMs with nearly twice the number of parameters. Furthermore, CoachLM is successfully deployed in a data management system for LLMs at Huawei, resulting in an efficiency improvement of up to 20% in the cleaning of 40k real-world instruction pairs. We release various assets of CoachLM, including the training data, code and test set (https://github.com/lunyiliu/CoachLM).
Open AccessCoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of high-quality instruction datasets is costly, leading to the adoption of automatic generation of instruction pairs by LLMs as a popular alternative. To ensure the high quality of LLM-generated instruction datasets, several approaches have been proposed. Nevertheless, existing methods either compromise dataset integrity by filtering a large proportion of samples, or are unsuitable for industrial applications. In this paper, instead of discarding low-quality samples, we propose CoachLM, a novel approach to enhance the quality of instruction datasets through automatic revisions on samples in the dataset. CoachLM is trained from the samples revised by human experts and significantly increases the proportion of high-quality samples in the dataset from 17.7% to 78.9%. The effectiveness of CoachLM is further assessed on various real-world instruction test sets. The results show that CoachLM improves the instruction-following capabilities of the instruction-tuned LLM by an average of 29.9%, which even surpasses larger LLMs with nearly twice the number of parameters. Furthermore, CoachLM is successfully deployed in a data management system for LLMs at Huawei, resulting in an efficiency improvement of up to 20% in the cleaning of 40k real-world instruction pairs. We release various assets of CoachLM, including the training data, code and test set (https://github.com/lunyiliu/CoachLM).
- 15 February 2024
- Published by Springer Nature
- p. 9-22
Semi-End-to-End Nested Named Entity Recognition from Speech
- 15 February 2024
- Published by Springer Nature
- p. 9-22
Semi-End-to-End Nested Named Entity Recognition from Speech
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4977-4983
Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Yuang Li, Min Zhang, Mengxin Ren, Xiaosong Qiao, Miaomiao Ma, Daimeng Wei, Hao Yang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4977-4983
Open AccessCross-Domain Audio Deepfake Detection: Dataset and Analysis
Yuang Li, Min Zhang, Mengxin Ren, Xiaosong Qiao, Miaomiao Ma, Daimeng Wei, Hao Yang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 535-540
HW-TSC 2024 Submission for the Quality Estimation Shared Task
Weiqiao Shan, Ming Zhu, Yuang Li, Mengyao Piao, Xiaofeng Zhao, Chang Su, Min Zhang, Hao Yang, Yanfei Jiang. Proceedings of the Ninth Conference on Machine Translation. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 535-540
Open AccessHW-TSC 2024 Submission for the Quality Estimation Shared Task
Weiqiao Shan, Ming Zhu, Yuang Li, Mengyao Piao, Xiaofeng Zhao, Chang Su, Min Zhang, Hao Yang, Yanfei Jiang. Proceedings of the Ninth Conference on Machine Translation. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 131-136
HW-TSC at TextGraphs-17 Shared Task: Enhancing Inference Capabilities of LLMs with Knowledge Graphs
Wei Tang, Xiaosong Qiao, Xiaofeng Zhao, Min Zhang, Chang Su, Yuang Li, Yinglu Li, Yilun Liu, Feiyu Yao, Shimin Tao, Hao Yang, He Xianghui. Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 131-136
Open AccessHW-TSC at TextGraphs-17 Shared Task: Enhancing Inference Capabilities of LLMs with Knowledge Graphs
Wei Tang, Xiaosong Qiao, Xiaofeng Zhao, Min Zhang, Chang Su, Yuang Li, Yinglu Li, Yilun Liu, Feiyu Yao, Shimin Tao, Hao Yang, He Xianghui. Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing. 2024.