Score: 1

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues

Published: May 31, 2025 | arXiv ID: 2506.00668v1

By: Martin Kuo , Jianyi Zhang , Aolin Ding and more

Potential Business Impact:

Stops bad guys tricking smart computers with talking.

Business Areas:
Semantic Search Internet Services

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense mechanism: SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues (STREAM). STREAM defends LLMs against multi-turn attacks while preserving their functional capabilities. Our approach involves constructing a human-annotated dataset, the Safety Reasoning Multi-turn Dialogues dataset, which is used to fine-tune a plug-and-play safety reasoning moderator. This model is designed to identify malicious intent hidden within multi-turn conversations and alert the target LLM of potential risks. We evaluate STREAM across multiple LLMs against prevalent multi-turn attack strategies. Experimental results demonstrate that our method significantly outperforms existing defense techniques, reducing the Attack Success Rate (ASR) by 51.2%, all while maintaining comparable LLM capability.

Repos / Data Links

Page Count
12 pages

Category
Computer Science:
Computation and Language