KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909224722759680 |
|---|---|
| author | Pei, Aihua Yang, Zehua Zhu, Shunan Cheng, Ruoxi Jia, Ju Wang, Lina |
| author_facet | Pei, Aihua Yang, Zehua Zhu, Shunan Cheng, Ruoxi Jia, Ju Wang, Lina |
| contents | Existing frameworks for assessing robustness of large language models (LLMs) overly depend on specific benchmarks, increasing costs and failing to evaluate performance of LLMs in professional domains due to dataset limitations. This paper proposes a framework that systematically evaluates the robustness of LLMs under adversarial attack scenarios by leveraging knowledge graphs (KGs). Our framework generates original prompts from the triplets of knowledge graphs and creates adversarial prompts by poisoning, assessing the robustness of LLMs through the results of these adversarial attacks. We systematically evaluate the effectiveness of this framework and its modules. Experiments show that adversarial robustness of the ChatGPT family ranks as GPT-4-turbo > GPT-4o > GPT-3.5-turbo, and the robustness of large language models is influenced by the professional domains in which they operate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10802 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs Pei, Aihua Yang, Zehua Zhu, Shunan Cheng, Ruoxi Jia, Ju Wang, Lina Computation and Language Artificial Intelligence Existing frameworks for assessing robustness of large language models (LLMs) overly depend on specific benchmarks, increasing costs and failing to evaluate performance of LLMs in professional domains due to dataset limitations. This paper proposes a framework that systematically evaluates the robustness of LLMs under adversarial attack scenarios by leveraging knowledge graphs (KGs). Our framework generates original prompts from the triplets of knowledge graphs and creates adversarial prompts by poisoning, assessing the robustness of LLMs through the results of these adversarial attacks. We systematically evaluate the effectiveness of this framework and its modules. Experiments show that adversarial robustness of the ChatGPT family ranks as GPT-4-turbo > GPT-4o > GPT-3.5-turbo, and the robustness of large language models is influenced by the professional domains in which they operate. |
| title | KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.10802 |