Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.09112 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917203133071360 |
|---|---|
| author | He, Ying Li, Baiyang Cao, Yule Xu, Huirun Chen, Qiuxian Chen, Shu Ren, Shangsheng |
| author_facet | He, Ying Li, Baiyang Cao, Yule Xu, Huirun Chen, Qiuxian Chen, Shu Ren, Shangsheng |
| contents | The rapid development of generative AI has brought value- and ethics-related risks to the forefront, making value safety a critical concern while a unified consensus remains lacking. In this work, we propose an internationally inclusive and resilient unified value framework, the GenAI Value Safety Scale (GVS-Scale): Grounded in a lifecycle-oriented perspective, we develop a taxonomy of GenAI value safety risks and construct the GenAI Value Safety Incident Repository (GVSIR), and further derive the GVS-Scale through grounded theory and operationalize it via the GenAI Value Safety Benchmark (GVS-Bench). Experiments on mainstream text generation models reveal substantial variation in value safety performance across models and value categories, indicating uneven and fragmented value alignment in current systems. Our findings highlight the importance of establishing shared safety foundations through dialogue and advancing technical safety mechanisms beyond reactive constraints toward more flexible approaches. Data and evaluation guidelines are available at https://github.com/acl2026/GVS-Bench. This paper includes examples that may be offensive or harmful. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09112 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Seeking Human Security Consensus: A Unified Value Scale for Generative AI Value Safety He, Ying Li, Baiyang Cao, Yule Xu, Huirun Chen, Qiuxian Chen, Shu Ren, Shangsheng Computers and Society The rapid development of generative AI has brought value- and ethics-related risks to the forefront, making value safety a critical concern while a unified consensus remains lacking. In this work, we propose an internationally inclusive and resilient unified value framework, the GenAI Value Safety Scale (GVS-Scale): Grounded in a lifecycle-oriented perspective, we develop a taxonomy of GenAI value safety risks and construct the GenAI Value Safety Incident Repository (GVSIR), and further derive the GVS-Scale through grounded theory and operationalize it via the GenAI Value Safety Benchmark (GVS-Bench). Experiments on mainstream text generation models reveal substantial variation in value safety performance across models and value categories, indicating uneven and fragmented value alignment in current systems. Our findings highlight the importance of establishing shared safety foundations through dialogue and advancing technical safety mechanisms beyond reactive constraints toward more flexible approaches. Data and evaluation guidelines are available at https://github.com/acl2026/GVS-Bench. This paper includes examples that may be offensive or harmful. |
| title | Seeking Human Security Consensus: A Unified Value Scale for Generative AI Value Safety |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2601.09112 |