C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912798919884800 |
|---|---|
| author | Wu, Ping Shen, Guobin Zhao, Dongcheng Wang, Yuwei Dong, Yiting Shi, Yu Lu, Enmeng Zhao, Feifei Zeng, Yi |
| author_facet | Wu, Ping Shen, Guobin Zhao, Dongcheng Wang, Yuwei Dong, Yiting Shi, Yu Lu, Enmeng Zhao, Feifei Zeng, Yi |
| contents | Ensuring that Large Language Models (LLMs) align with mainstream human values and ethical norms is crucial for the safe and sustainable development of AI. Current value evaluation and alignment are constrained by Western cultural bias and incomplete domestic frameworks reliant on non-native rules; furthermore, the lack of scalable, rule-driven scenario generation methods makes evaluations costly and inadequate across diverse cultural contexts. To address these challenges, we propose a hierarchical value framework grounded in core Chinese values, encompassing three main dimensions, 12 core values, and 50 derived values. Based on this framework, we construct a large-scale Chinese Value Rule Corpus (C-VARC) containing over 250,000 value rules enhanced and expanded through human annotation. Experimental results demonstrate that scenarios guided by C-VARC exhibit clearer value boundaries and greater content diversity compared to those produced through direct generation. In the evaluation across six sensitive themes (e.g., surrogacy, suicide), seven mainstream LLMs preferred C-VARC generated options in over 70.5% of cases, while five Chinese human annotators showed an 87.5% alignment with C-VARC, confirming its universality, cultural relevance, and strong alignment with Chinese values. Additionally, we construct 400,000 rule-based moral dilemma scenarios that objectively capture nuanced distinctions in conflicting value prioritization across 17 LLMs. Our work establishes a culturally-adaptive benchmarking framework for comprehensive value evaluation and alignment, representing Chinese characteristics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models Wu, Ping Shen, Guobin Zhao, Dongcheng Wang, Yuwei Dong, Yiting Shi, Yu Lu, Enmeng Zhao, Feifei Zeng, Yi Computation and Language Ensuring that Large Language Models (LLMs) align with mainstream human values and ethical norms is crucial for the safe and sustainable development of AI. Current value evaluation and alignment are constrained by Western cultural bias and incomplete domestic frameworks reliant on non-native rules; furthermore, the lack of scalable, rule-driven scenario generation methods makes evaluations costly and inadequate across diverse cultural contexts. To address these challenges, we propose a hierarchical value framework grounded in core Chinese values, encompassing three main dimensions, 12 core values, and 50 derived values. Based on this framework, we construct a large-scale Chinese Value Rule Corpus (C-VARC) containing over 250,000 value rules enhanced and expanded through human annotation. Experimental results demonstrate that scenarios guided by C-VARC exhibit clearer value boundaries and greater content diversity compared to those produced through direct generation. In the evaluation across six sensitive themes (e.g., surrogacy, suicide), seven mainstream LLMs preferred C-VARC generated options in over 70.5% of cases, while five Chinese human annotators showed an 87.5% alignment with C-VARC, confirming its universality, cultural relevance, and strong alignment with Chinese values. Additionally, we construct 400,000 rule-based moral dilemma scenarios that objectively capture nuanced distinctions in conflicting value prioritization across 17 LLMs. Our work establishes a culturally-adaptive benchmarking framework for comprehensive value evaluation and alignment, representing Chinese characteristics. |
| title | C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.01495 |