Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917822677909504 |
|---|---|
| author | Zhou, Zhenhong Xiang, Jiuyang Chen, Haopeng Liu, Quan Li, Zherui Su, Sen |
| author_facet | Zhou, Zhenhong Xiang, Jiuyang Chen, Haopeng Liu, Quan Li, Zherui Su, Sen |
| contents | Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have predominantly focused on single-turn dialogue, ignoring the potential complexities and risks presented by multi-turn dialogue, a crucial mode through which humans derive information from LLMs. In this paper, we argue that humans could exploit multi-turn dialogue to induce LLMs into generating harmful information. LLMs may not intend to reject cautionary or borderline unsafe queries, even if each turn is closely served for one malicious purpose in a multi-turn dialogue. Therefore, by decomposing an unsafe query into several sub-queries for multi-turn dialogue, we induced LLMs to answer harmful sub-questions incrementally, culminating in an overall harmful response. Our experiments, conducted across a wide range of LLMs, indicate current inadequacies in the safety mechanisms of LLMs in multi-turn dialogue. Our findings expose vulnerabilities of LLMs in complex scenarios involving multi-turn dialogue, presenting new challenges for the safety of LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17262 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue Zhou, Zhenhong Xiang, Jiuyang Chen, Haopeng Liu, Quan Li, Zherui Su, Sen Computation and Language Artificial Intelligence Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have predominantly focused on single-turn dialogue, ignoring the potential complexities and risks presented by multi-turn dialogue, a crucial mode through which humans derive information from LLMs. In this paper, we argue that humans could exploit multi-turn dialogue to induce LLMs into generating harmful information. LLMs may not intend to reject cautionary or borderline unsafe queries, even if each turn is closely served for one malicious purpose in a multi-turn dialogue. Therefore, by decomposing an unsafe query into several sub-queries for multi-turn dialogue, we induced LLMs to answer harmful sub-questions incrementally, culminating in an overall harmful response. Our experiments, conducted across a wide range of LLMs, indicate current inadequacies in the safety mechanisms of LLMs in multi-turn dialogue. Our findings expose vulnerabilities of LLMs in complex scenarios involving multi-turn dialogue, presenting new challenges for the safety of LLMs. |
| title | Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.17262 |