Siqi Wang, Lanqing Hong, Jing Li, Fei Mi, Erxin Yu, Ming Liao, Zuchen Gao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research issue. Previous red teaming approaches for LLM safety have primarily focused on single prompt attack or goal hijacking. To the best of our knowledge, we are the first to study LLM safety in multi-turn dialogue coreference. We created a dataset of 1, 400 questions across 14 categories, each featuring multi-turn coreference safety attacks. We then conducted detailed evaluations on five widely used open-source LLMs. The results indicated that under multi-turn coreference safety attacks, the highest attack successful rate was 56% with the LLaMA2-Chat-7b model, while the lowest was 13.9% with the Mistral-7B-Instruct model. These findings highlight the safety vulnerabilities in LLMs during dialogue coreference interactions. Warning: This paper may contain offensive language or harmful content. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.17626")
get_code_for_paper("2406.17626")
have("2406.17626")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.17626.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.17626)
Connect an agent — have() is free.