Pengyuan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pengyuan Liu has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Dong Yu
School of Information Science Beijing Language and Culture University Beijing China
4 shared publications - Ying Liu
Tsinghua University
4 shared publications Chengyu Du
Beijing Language and Culture University
3 shared publicationsMengyang Hu
Beijing Language and Culture University
3 shared publicationsBingjie Du
School of Information Science Beijing Language and Culture University Beijing China
2 shared publicationsDong Yu
Beijing Language and Culture University
2 shared publications
Latest Publications
- 27 March 2025
- Published by Springer Nature
- p. 100-116
Construction of Query Classification System and Query Classification Corpus for Chinese Intent Recognition
- 27 March 2025
- Published by Springer Nature
- p. 100-116
Construction of Query Classification System and Query Classification Corpus for Chinese Intent Recognition
- 27 March 2025
- Published by Springer Nature
- p. 301-315
Quantitative Study on the Moral Tendency and Moral Types of Chinese Adverbs
- 27 March 2025
- Published by Springer Nature
- p. 301-315
Quantitative Study on the Moral Tendency and Moral Types of Chinese Adverbs
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11649-11662
Attribution and Application of Multiple Neurons in Multimodal Large Language Models
Feiyu Wang, Ziran Zhao, Dong Yu, Pengyuan Liu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11649-11662
Open AccessAttribution and Application of Multiple Neurons in Multimodal Large Language Models
Feiyu Wang, Ziran Zhao, Dong Yu, Pengyuan Liu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7757-7797
Investigating Value-Reasoning Reliability in Small Large Language Models
Xia Du, Shuhan Sun, Pengyuan Liu, Dong Yu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7757-7797
Open AccessInvestigating Value-Reasoning Reliability in Small Large Language Models
Xia Du, Shuhan Sun, Pengyuan Liu, Dong Yu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 29 November 2024
- Published by Springer Nature
- p. 57-72
Generate-then-Revise: An Effective Synthetic Training Data Generation Framework for Event Detection
- 29 November 2024
- Published by Springer Nature
- p. 57-72
Generate-then-Revise: An Effective Synthetic Training Data Generation Framework for Event Detection
- Open Access
Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.
Open AccessEvaluating Moral Beliefs across LLMs through a Pluralistic Framework
Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4740-4760
Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
Xuelin Liu, Yanfei Zhu, Shucheng Zhu, Pengyuan Liu, Ying Liu, Dong Yu. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4740-4760
Open AccessEvaluating Moral Beliefs across LLMs through a Pluralistic Framework
Xuelin Liu, Yanfei Zhu, Shucheng Zhu, Pengyuan Liu, Ying Liu, Dong Yu. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 20-32
Do PLMs and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias
Shucheng Zhu, Bingjie Du, Jishun Zhao, Ying Liu, Pengyuan Liu. Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 20-32
Open AccessDo PLMs and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias
Shucheng Zhu, Bingjie Du, Jishun Zhao, Ying Liu, Pengyuan Liu. Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP). 2024.
- 28 October 2023
- Published by Springer Nature
- p. 233-245
CCD-ASQP: A Chinese Cross-Domain Aspect Sentiment Quadruple Prediction Dataset
- 28 October 2023
- Published by Springer Nature
- p. 233-245
CCD-ASQP: A Chinese Cross-Domain Aspect Sentiment Quadruple Prediction Dataset
- Open Access
Proposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark
Existing propositions often rely on logical constants for classification. Compared with Western languages that lean towards hypotaxis such as English, Chinese often relies on semantic or logical understanding rather than logical connectives in daily expressions, exhibiting the characteristics of parataxis. However, existing research has rarely paid attention to this issue. And accurately classifying these propositions is crucial for natural language understanding and reasoning. In this paper, we put forward the concepts of explicit and implicit propositions and propose a comprehensive multi-level proposition classification system based on linguistics and logic. Correspondingly, we create a large-scale Chinese proposition dataset PEACE from multiple domains, covering all categories related to propositions. To evaluate the Chinese proposition classification ability of existing models and explore their limitations, We conduct evaluations on PEACE using several different methods including the Rule-based method, SVM, BERT, RoBERTA, and ChatGPT. Results show the importance of properly modeling the semantic features of propositions. BERT has relatively good proposition classification capability, but lacks cross-domain transferability. ChatGPT performs poorly, but its classification ability can be improved by providing more proposition information. Many issues are still far from being resolved and require further study.
Open AccessProposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark
Existing propositions often rely on logical constants for classification. Compared with Western languages that lean towards hypotaxis such as English, Chinese often relies on semantic or logical understanding rather than logical connectives in daily expressions, exhibiting the characteristics of parataxis. However, existing research has rarely paid attention to this issue. And accurately classifying these propositions is crucial for natural language understanding and reasoning. In this paper, we put forward the concepts of explicit and implicit propositions and propose a comprehensive multi-level proposition classification system based on linguistics and logic. Correspondingly, we create a large-scale Chinese proposition dataset PEACE from multiple domains, covering all categories related to propositions. To evaluate the Chinese proposition classification ability of existing models and explore their limitations, We conduct evaluations on PEACE using several different methods including the Rule-based method, SVM, BERT, RoBERTA, and ChatGPT. Results show the importance of properly modeling the semantic features of propositions. BERT has relatively good proposition classification capability, but lacks cross-domain transferability. ChatGPT performs poorly, but its classification ability can be improved by providing more proposition information. Many issues are still far from being resolved and require further study.