ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain

• URL: http://arxiv.org/abs/2411.16736v1
• Date: Sat, 23 Nov 2024 12:50:33 GMT
• Title: ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
• Authors: Haochen Zhao, Xiangru Tang, Ziran Yang, Xiao Han, Xuanzhi Feng, Yueqing Fan, Senhao Cheng, Di Jin, Yilun Zhao, Arman Cohan, Mark Gerstein,
• Abstract summary: ChemSafetyBench is a benchmark designed to evaluate the accuracy and safety of large language models (LLMs) ChemSafetyBench encompasses three key tasks: querying chemical properties, assessing the legality of chemical uses, and describing synthesis methods. Our dataset has more than 30K samples across various chemical materials.
• Score: 28.205744043861756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The advancement and extensive application of large language models (LLMs) have been remarkable, including their use in scientific research assistance. However, these models often generate scientifically incorrect or unsafe responses, and in some cases, they may encourage users to engage in dangerous behavior. To address this issue in the field of chemistry, we introduce ChemSafetyBench, a benchmark designed to evaluate the accuracy and safety of LLM responses. ChemSafetyBench encompasses three key tasks: querying chemical properties, assessing the legality of chemical uses, and describing synthesis methods, each requiring increasingly deeper chemical knowledge. Our dataset has more than 30K samples across various chemical materials. We incorporate handcrafted templates and advanced jailbreaking scenarios to enhance task diversity. Our automated evaluation framework thoroughly assesses the safety, accuracy, and appropriateness of LLM responses. Extensive experiments with state-of-the-art LLMs reveal notable strengths and critical vulnerabilities, underscoring the need for robust safety measures. ChemSafetyBench aims to be a pivotal tool in developing safer AI technologies in chemistry. Our code and dataset are available at https://github.com/HaochenZhao/SafeAgent4Chem. Warning: this paper contains discussions on the synthesis of controlled chemicals using AI models.

Related papers

• The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? [54.18519360412294]
  Large Language Models (LLMs) must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility. This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance. We analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model.
  arXiv  Detail & Related papers  (2025-01-20T06:35:01Z)
• ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning [64.2106664137118]
  ChemAgent is a novel framework designed to improve the performance of large language models (LLMs) It is developed by decomposing chemical tasks into sub-tasks and compiling these sub-tasks into a structured collection that can be referenced for future queries. When presented with a new problem, ChemAgent retrieves and refines pertinent information from the library, which we call memory.
  arXiv  Detail & Related papers  (2025-01-11T17:10:30Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis [12.577741068644077]
  This paper explores the security vulnerabilities of large language models (LLMs) within the field of chemistry. We evaluate the effectiveness of several prompt injection attack methods, including red-teaming, explicit prompting, and implicit prompting. We introduce a novel attack technique named SMILES-prompting, which uses the simplified Molecular-Input Line-Entry System (SMILES) to reference chemical substances.
  arXiv  Detail & Related papers  (2024-10-21T05:01:50Z)
• LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs [80.45174785447136]
  Laboratory accidents pose significant risks to human life and property. Despite advancements in safety training, laboratory personnel may still unknowingly engage in unsafe practices. There is a growing concern about large language models (LLMs) for guidance in various fields.
  arXiv  Detail & Related papers  (2024-10-18T05:21:05Z)
• SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks [36.99233361224705]
  Large language models (LLMs) have had a transformative impact on a variety of scientific tasks across disciplines such as biology, chemistry, medicine, and physics. Existing benchmarks primarily focus on textual content and overlooking key scientific representations such as molecular, protein, and genomic languages. We introduce SciSafeEval, a benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks.
  arXiv  Detail & Related papers  (2024-10-02T16:34:48Z)
• ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models [62.37850540570268]
  Existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. ChemEval identifies 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks. Results show that while general LLMs excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge.
  arXiv  Detail & Related papers  (2024-09-21T02:50:43Z)
• Are large language models superhuman chemists? [4.87961182129702]
  Large language models (LLMs) have gained widespread interest due to their ability to process human language and perform tasks on which they have not been explicitly trained. Here, we introduce "ChemBench," an automated framework for evaluating the chemical knowledge and reasoning abilities of state-of-the-art LLMs. We curated more than 2,700 question-answer pairs, evaluated leading open- and closed-source LLMs, and found that the best models outperformed the best human chemists.
  arXiv  Detail & Related papers  (2024-04-01T20:56:25Z)
• ChemLLM: A Chemical Large Language Model [49.308528569982805]
  Large language models (LLMs) have made impressive progress in chemistry applications. However, the community lacks an LLM specifically designed for chemistry. Here, we introduce ChemLLM, a comprehensive framework that features the first LLM dedicated to chemistry.
  arXiv  Detail & Related papers  (2024-02-10T01:11:59Z)
• SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models [107.82336341926134]
  SALAD-Bench is a safety benchmark specifically designed for evaluating Large Language Models (LLMs) It transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.
  arXiv  Detail & Related papers  (2024-02-07T17:33:54Z)
• ChemVise: Maximizing Out-of-Distribution Chemical Detection with the Novel Application of Zero-Shot Learning [60.02503434201552]
  This research proposes learning approximations of complex exposures from training sets of simple ones. We demonstrate this approach to synthetic sensor responses surprisingly improves the detection of out-of-distribution obscured chemical analytes.
  arXiv  Detail & Related papers  (2023-02-09T20:19:57Z)

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.