Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.21419 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916868282908672 |
|---|---|
| author | Wang, Haiquan Chen, Yi Zeng, Shang Bian, Yun Cui, Zhe |
| author_facet | Wang, Haiquan Chen, Yi Zeng, Shang Bian, Yun Cui, Zhe |
| contents | Current evaluations of LLMs in the government domain primarily focus on safety considerations in specific scenarios, while the assessment of the models' own core capabilities, particularly domain relevance, remains insufficient. To address this gap, we propose GovRelBench, a benchmark specifically designed for evaluating the core capabilities of LLMs in the government domain. GovRelBench consists of government domain prompts and a dedicated evaluation tool, GovRelBERT. During the training process of GovRelBERT, we introduce the SoftGovScore method: this method trains a model based on the ModernBERT architecture by converting hard labels to soft scores, enabling it to accurately compute the text's government domain relevance score. This work aims to enhance the capability evaluation framework for large models in the government domain, providing an effective tool for relevant research and practice. Our code and dataset are available at https://github.com/pan-xi/GovRelBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GovRelBench:A Benchmark for Government Domain Relevance Wang, Haiquan Chen, Yi Zeng, Shang Bian, Yun Cui, Zhe Artificial Intelligence Current evaluations of LLMs in the government domain primarily focus on safety considerations in specific scenarios, while the assessment of the models' own core capabilities, particularly domain relevance, remains insufficient. To address this gap, we propose GovRelBench, a benchmark specifically designed for evaluating the core capabilities of LLMs in the government domain. GovRelBench consists of government domain prompts and a dedicated evaluation tool, GovRelBERT. During the training process of GovRelBERT, we introduce the SoftGovScore method: this method trains a model based on the ModernBERT architecture by converting hard labels to soft scores, enabling it to accurately compute the text's government domain relevance score. This work aims to enhance the capability evaluation framework for large models in the government domain, providing an effective tool for relevant research and practice. Our code and dataset are available at https://github.com/pan-xi/GovRelBench. |
| title | GovRelBench:A Benchmark for Government Domain Relevance |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.21419 |