SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

• URL: http://arxiv.org/abs/2502.12025v1
• Date: Mon, 17 Feb 2025 16:57:56 GMT
• Title: SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
• Authors: Fengqing Jiang, Zhangchen Xu, Yuetai Li, Luyao Niu, Zhen Xiang, Bo Li, Bill Yuchen Lin, Radha Poovendran,
• Abstract summary: Long chain-of-thought (CoT) reasoning generates structured intermediate steps, enhancing reasoning capabilities. Current research on large language model (LLM) safety usually focuses on short-answer responses, overlooking the long CoT style outputs of LRMs.
• Score: 21.317245896641136
• License:
• Abstract: Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reasoning capabilities. However, long CoT does not inherently guarantee safe outputs, potentially leading to harmful consequences such as the introduction of security vulnerabilities in code or the spread of misinformation. Current research on large language model (LLM) safety usually focuses on short-answer responses, overlooking the long CoT style outputs of LRMs. To bridge this gap, we conduct a systematic study of LRM safety. First, we investigate safety evaluators calibrated against human annotations. Using our newly developed metrics, we thoroughly assess the safety of 12 state-of-the-art LRMs on StrongReject and WildJailbreak datasets. Our results show that LRMs are not safe compared to their reasoning advance. Further, we perform a fine-grained analysis of the reasoning trace and final answer. We find that three decoding strategies-ZeroThink, LessThink, and MoreThink-can improve model safety without additional training. However, these strategies either use constrained reasoning traces or incur high inference costs. To better strengthen LRM safety, we introduce SafeChain, the first-of-its-kind safety training dataset in CoT style. We fine-tune two LRMs with SafeChain, showing that it not only enhances model safety but also preserves performance across 6 reasoning benchmarks.

Related papers

• H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking [22.760366525219762]
  Large Reasoning Models (LRMs) have recently extended their powerful reasoning capabilities to safety checks. We introduce Malicious-Educator, a benchmark that disguises extremely dangerous or malicious requests beneath seemingly legitimate educational prompts. Our experiments reveal severe security flaws in popular commercial-grade LRMs, including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking.
  arXiv  Detail & Related papers  (2025-02-18T14:29:12Z)
• The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 [70.94607997570729]
  We present a comprehensive safety assessment of OpenAI-o3 and DeepSeek-R1 reasoning models. We investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications.
  arXiv  Detail & Related papers  (2025-02-18T09:06:07Z)
• STAIR: Improving Safety Alignment with Introspective Reasoning [44.780098674618614]
  We propose STAIR, a framework that integrates SafeTy Alignment with Itrospective Reasoning. We show that STAIR effectively mitigates harmful outputs while better preserving helpfulness, compared to instinctive alignment strategies. With test-time scaling, STAIR achieves a safety performance comparable to Claude-3.5 against popular jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-04T15:02:55Z)
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models [25.606641582511106]
  We propose a novel dataset that integrates multi-image inputs with safety Chain-of-Thought (CoT) labels as fine-grained reasoning logic to improve model performance. Our experiments demonstrate that fine-tuning InternVL2.5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks.
  arXiv  Detail & Related papers  (2025-01-30T17:59:45Z)
• OpenAI o1 System Card [274.83891368890977]
  The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations.
  arXiv  Detail & Related papers  (2024-12-21T18:04:31Z)
• Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level [10.476222570886483]
  Large language models (LLMs) have demonstrated immense utility across various industries. As LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. This paper examines the LLMs' capability to recognize harmful outputs, revealing and quantifying their proficiency in assessing the danger of previous tokens.
  arXiv  Detail & Related papers  (2024-10-09T12:09:30Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
  ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
  arXiv  Detail & Related papers  (2024-04-06T15:01:47Z)
• Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation [79.89605349842569]
  We introduce the Collection and Refinement of Online Properties (CROP) framework to design properties at training time. CROP employs a cost signal to identify unsafe interactions and use them to shape safety properties. We evaluate our approach in several robotic mapless navigation tasks and demonstrate that the violation metric computed with CROP allows higher returns and lower violations over previous Safe DRL approaches.
  arXiv  Detail & Related papers  (2023-02-13T21:19:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.