SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge

• URL: http://arxiv.org/abs/2505.21605v2
• Date: Sat, 14 Jun 2025 19:43:42 GMT
• Title: SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
• Authors: Fengqing Jiang, Fengbo Ma, Zhangchen Xu, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bo Li, Xianyan Chen, Zhen Xiang, Radha Poovendran,
• Abstract summary: SOSBench is a regulation-grounded, hazard-focused benchmark for large language models.<n>It covers six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology.<n>We evaluate frontier models within a unified evaluation framework using our SOSBench.
• Score: 11.63268709958876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SOSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 79.1% for Deepseek-R1 and 47.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

Related papers

• SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents [11.817130554581436]
  We introduce textbfSafeScientist, an innovative AI scientist framework to enhance safety and ethical responsibility in AI-driven scientific exploration.<n>SafeScientist proactively refuses ethically inappropriate or high-risk tasks and rigorously emphasizes safety throughout the research process.<n>We propose textbfSciSafetyBench, a novel benchmark specifically designed to evaluate AI safety in scientific contexts.
  arXiv  Detail & Related papers  (2025-05-29T15:35:58Z)
• Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models [29.569220030102986]
  We introduce textbfBeyond Safe Answers (BSA) bench, a novel benchmark comprising 2,000 challenging instances organized into three distinct SSA scenario types.<n> Evaluations of 19 state-of-the-art LRMs demonstrate the difficulty of this benchmark, with top-performing models achieving only 38.0% accuracy in correctly identifying risk rationales.<n>Our work provides a comprehensive assessment tool for evaluating and improving safety reasoning fidelity in LRMs, advancing the development of genuinely risk-aware and reliably safe AI systems.
  arXiv  Detail & Related papers  (2025-05-26T08:49:19Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents [10.565508277042564]
  Large language models (LLMs) are evolving into autonomous decision-makers, raising concerns about catastrophic risks in high-stakes scenarios.<n>Based on the insight that such risks can originate from trade-offs between the agent's Helpful, Harmlessness and Honest (HHH) goals, we build a novel three-stage evaluation framework.<n>We conduct 14,400 agentic simulations across 12 advanced LLMs, with extensive experiments and analysis.
  arXiv  Detail & Related papers  (2025-02-17T02:11:17Z)
• Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering [9.559203170987598]
  Construction remains one of the most hazardous sectors. Recent advancements in AI, particularly Large Language Models (LLMs), offer promising opportunities for enhancing workplace safety. This study evaluates the performance of two widely used LLMs, GPT-3.5 and GPT-4o, across three standardized exams administered by the Board of Certified Safety Professionals (BCSP)
  arXiv  Detail & Related papers  (2024-11-13T04:06:09Z)
• LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs [78.99703366417661]
  Large language models (LLMs) increasingly assist in tasks ranging from procedural guidance to autonomous experiment orchestration.<n>Such overreliance is particularly dangerous in high-stakes laboratory settings, where failures in hazard identification or risk assessment can result in severe accidents.<n>We propose the Laboratory Safety Benchmark (LabSafety Bench) to evaluate models on their ability to identify potential hazards, assess risks, and predict the consequences of unsafe actions in lab environments.
  arXiv  Detail & Related papers  (2024-10-18T05:21:05Z)
• Risks and NLP Design: A Case Study on Procedural Document QA [52.557503571760215]
  We argue that clearer assessments of risks and harms to users will be possible when we specialize the analysis to more concrete applications and their plausible users. We conduct a risk-oriented error analysis that could then inform the design of a future system to be deployed with lower risk of harm and better performance.
  arXiv  Detail & Related papers  (2024-08-16T17:23:43Z)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models [65.34666117785179]
  Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs.<n>This study proposes a novel method for automatically generating large-scale over-refusal datasets.<n>We introduce OR-Bench, the first large-scale over-refusal benchmark.
  arXiv  Detail & Related papers  (2024-05-31T15:44:33Z)
• 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)
• Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science [65.77763092833348]
  Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these agents also introduce novel vulnerabilities that demand careful consideration for safety. This paper conducts a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures.
  arXiv  Detail & Related papers  (2024-02-06T18:54:07Z)
• Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI [76.28956947107372]
  Covertly unsafe text is an area of particular interest, as such text may arise from everyday scenarios and are challenging to detect as harmful. We propose FARM, a novel framework leveraging external knowledge for trustworthy rationale generation in the context of safety. Our experiments show that FARM obtains state-of-the-art results on the SafeText dataset, showing absolute improvement in safety classification accuracy by 5.9%.
  arXiv  Detail & Related papers  (2022-12-19T17:51:47Z)

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.