Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.
데이터셋
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
This dataset consists of 225 malicious tasks, which were integrated into ten distinct jailbreaking prompts. The malicious tasks were divided into five categories, namely, 1. Misinformation and Disinformation 2. Security Threats and Cybercrimes 3. Unlawful Behaviors and Activities 4. Hate Speech and Discrimination 5. Substance Abuse and Dangerous Practices. The jailbreaking prompts were carefully selected to cover a diverse range of scenarios. These scenarios included role-playing, simulations, attention-shifting, and privileged execution, and the placement of the malicious task within the jailbreaking prompts was also varied. List of malicious tasks only: https://github.com/CrystalEye42/eval-safety/blob/main/malicious_tasks_dataset.yaml Malicious tasks with jailbreaking prompts: https://github.com/CrystalEye42/eval-safety/blob/main/integrated.yaml
Texygen is a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the diversity, the quality and the consistency of the generated texts. The Texygen platform could help standardize the research on text generation and facilitate the sharing of fine-tuned open-source implementations among researchers for their work. As a consequence, this would help in improving the reproductivity and reliability of future research work in text generation. Source: Texygen Platform