MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation-Reference-Cited by-同舟云学术

MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation

Published:2024-04-14 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering
language:
Short-container-title:

Author:

Wang Guanyu¹^ORCID,Li Yuekang²^ORCID,Liu Yi³^ORCID,Deng Gelei³^ORCID,Li Tianlin³^ORCID,Xu Guosheng¹^ORCID,Liu Yang³^ORCID,Wang Haoyu⁴^ORCID,Wang Kailong⁴^ORCID

Affiliation:

1. Beijing University of Posts and Telecommunications, Beijing, China

2. University of New South Wales, Sydney, Australia

3. Nanyang Technological University, Singapore, Singapore

4. Huazhong University of Science and Technology, Wuhan, China

Funder

National Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3650105.3652297

Reference87 articles.

1. 2023. MeTMaP. https://anonymous.4open.science/r/MeTMaP-879B. (2023).

2. 0xk1h0. 2023. ChatGPT_DAN. https://github.com/0xk1h0/ChatGPT_DAN. (2023).

3. Basemah Alshemali and Jugal Kalita. 2020. Improving the reliability of deep neural networks in NLP: A review. Knowledge-Based Systems 191 (2020).

4. On the generalised distance in statistics;Chandra Mahalanobis Prasanta;Proceedings of the National Institute of Sciences of India,1936

5. Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, and Yang Liu. 2024. Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues. arXiv preprint arXiv:2402.09091 (2024).

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Large Language Models Can Connect the Dots: Exploring Model Optimization Bugs with Domain Knowledge-Aware Prompts;Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis;2024-09-11

2. Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection;Proceedings of the ACM on Software Engineering;2024-07-12