Risks of Discrimination Violence and Unlawful Actions in LLM-Driven Robots
DOI:
https://doi.org/10.54097/taqbjh83Keywords:
Human-Robot Interaction (HRI), Large Language Models (LLMs), AI Ethics, Safety, Bias, Risk Assessment, FairnessAbstract
The integration of Large Language Models (LLMs) into robotics heralds significant advancements in human-robot interaction, enabling robots to perform complex tasks involving natural language understanding, common sense reasoning, and human modeling. However, despite their impressive capabilities, LLMs pose substantial ethical and safety concerns, particularly the risk of enacting discrimination, violence, and unlawful actions. This study conducts a comprehensive Human-Robot Interaction (HRI)-based evaluation of several highly-rated LLMs, focusing on their bias and safety criteria. Our findings reveal that LLMs exhibit significant biases across diverse demographic groups and frequently produce unsafe or unlawful responses when faced with unconstrained natural language inputs. These results underscore the urgent need for systematic risk assessments and robust ethical guidelines to ensure the responsible deployment of LLM-driven robots. We propose detailed strategies for mitigating these risks, including advanced bias detection techniques, robust safety mechanisms, and collaborative standards development. By addressing these critical issues, we aim to pave the way for the development of safer, fairer, and more reliable robotic systems.
References
Azeem, R., Hundt, A., Mansouri, M., & Brandão, M. (2024). LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions. arXiv preprint arXiv:2406.08824.
Lin, Y. (2023). Optimization and Use of Cloud Computing in Big Data Science. Computing, Performance and Communication Systems, 7(1), 119-124.
Achintalwar, S., Garcia, A. A., Anaby-Tavor, A., Baldini, I., Berger, S. E. (2024). Detectors for safe and reliable llms: Implementations, uses, and limitations. arXiv preprint arXiv:2403.06009.
Yang, Y., Guo, Z., Gellman, A. J., & Kitchin, J. (2022, November). Modeling Ternary Alloy Segregation with Density Functional Theory and Machine Learning. In 2022 AIChE Annual Meeting. AIChE.
Dogra, V., Verma, S., Woźniak, M., Shafi, J., & Ijaz, M. F. (2024). Shortcut Learning Explanations for Deep Natural Language Processing: A Survey on Dataset Biases. IEEE Access.
Lin, Y. (2024). Application and Challenges of Computer Networks in Distance Education. Computing, Performance and Communication Systems, 8(1), 17-24.
Chiu, K. L., Collins, A., & Alexander, R. (2021). Detecting hate speech with gpt-3. arXiv preprint arXiv:2103.12407.
Lin, Y. (2024). Design of urban road fault detection system based on artificial neural network and deep learning. Frontiers in neuroscience, 18, 1369832.
Wachter, S., Mittelstadt, B., & Russell, C. (2024). Do large language models have a legal duty to tell the truth?. Available at SSRN 4771884.
Yang, Y., Liu, M., & Kitchin, J. R. (2022). Neural network embeddings based similarity search method for atomistic systems. Digital Discovery, 1(5), 636-644.
Banerjee, S., Layek, S., Hazra, R., & Mukherjee, A. (2024). How (un) ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries. arXiv preprint arXiv:2402.15302.
Liu, M., & Li, Y. (2023, October). Numerical analysis and calculation of urban landscape spatial pattern. In 2nd International Conference on Intelligent Design and Innovative Technology (ICIDIT 2023) (pp. 113-119). Atlantis Press.
Chander, B., John, C., Warrier, L., & Gopalakrishnan, K. (2024). Toward Trustworthy Artificial Intelligence (TAI) in the Context of Explainability and Robustness. ACM Computing Surveys.
Wang, C., Yang, H., Chen, Y., Sun, L., Zhou, Y., & Wang, H. (2010). Identification of Image-spam Based on SIFT Image Matching Algorithm. JOURNAL OF INFORMATION &COMPUTATIONAL SCIENCE, 7(14), 3153-3160.
Spann, M., Bertini, M., Koenigsberg, O., Zeithammer, R., Aparicio, D., Chen, Y., ... & Yoo, H. (2024). Algorithmic Pricing: Implications for Consumers, Managers, and Regulators (No. w32540). National Bureau of Economic Research.
Yang, Y., Achar, S. K., & Kitchin, J. R. (2022). Evaluation of the degree of rate control via automatic differentiation. AIChE Journal, 68(6), e17653.
Eigner, E., & Händler, T. (2024). Determinants of llm-assisted decision-making. arXiv preprint arXiv:2402.17385.
Yang, Y., Jiménez-Negrón, O. A., & Kitchin, J. R. (2021). Machine-learning accelerated geometry optimization in molecular simulation. The Journal of Chemical Physics, 154(23).
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion, 58, 82-115.
Yang, Y., Guo, Z., Gellman, A. J., & Kitchin, J. R. (2022). Simulating segregation in a ternary Cu–Pd–Au alloy with density functional theory, machine learning, and Monte Carlo simulations. The Journal of Physical Chemistry C, 126(4), 1800-1808.
Verma, P., Kushwaha, H., & Singh, H. (2023). Artificial Intelligence in Healthcare: Inherent Biases and Concerns. In Artificial Intelligence and Machine Learning in Healthcare (pp. 179-187). Singapore: Springer Nature Singapore.
Yang, J. (2024). Data-Driven Investment Strategies in International Real Estate Markets: A Predictive Analytics Approach. International Journal of Computer Science and Information Technology, 3(1), 247-258.
Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., & McAuley, J. (2021). Adversarial deepfakes: Evaluating vulnerability of deepfake detectors to adversarial examples. In Proceedings of the IEEE/CVF winter conference on applications of computer vision (pp. 3348-3357).
Lin, Y. (2023). Construction of Computer Network Security System in the Era of Big Data. Advances in Computer and Communication, 4(3).
Caliskan, A., Ajay, P. P., Charlesworth, T., Wolfe, R., & Banaji, M. R. (2022, July). Gender bias in word embeddings: A comprehensive analysis of frequency, syntax, and semantics. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (pp. 156-170).
Wang, C., Yang, H., Chen, Y., Sun, L., Wang, H., & Zhou, Y. (2012). Identification of Image-spam Based on Perimetric Complexity Analysis and SIFT Image Matching Algorithm. JOURNAL OF INFORMATION &COMPUTATIONAL SCIENCE, 9(4), 1073-1081.
Wang, A., Bai, X., Barocas, S., & Blodgett, S. L. (2024). Measuring machine learning harms from stereotypes: requires understanding who is being harmed by which errors in what ways. arXiv preprint arXiv:2402.04420.
Lian, J., & Chen, T. (2024). Research on Complex Data Mining Analysis and Pattern Recognition Based on Deep Learning. Journal of Computing and Electronic Information Management, 12(3), 37-41.
Kumar, A., Agarwal, C., Srinivas, S., Feizi, S., & Lakkaraju, H. (2023). Certifying llm safety against adversarial prompting. arXiv preprint arXiv:2309.02705.
Yao, Y. (2022). A Review of the Comprehensive Application of Big Data, Artificial Intelligence, and Internet of Things Technologies in Smart Cities. Journal of Computational Methods in Engineering Applications, 1-10.
Koh, H., Kim, D., Lee, M., & Jung, K. (2024). Can LLMs Recognize Toxicity? Structured Toxicity Investigation Framework and Semantic-Based Metric. arXiv preprint arXiv:2402.06900.
Chen, T., Lian, J., & Sun, B. (2024). An Exploration of the Development of Computerized Data Mining Techniques and Their Application. International Journal of Computer Science and Information Technology, 3(1), 206-212.
Hamon, R., Junklewitz, H., & Sanchez, I. (2020). Robustness and explainability of artificial intelligence. Publications Office of the European Union, 207, 2020.
Qiu, L., & Liu, M. (2024). Innovative Design of Cultural Souvenirs Based on Deep Learning and CAD.
Yao, Y. (2024). Digital Government Information Platform Construction: Technology, Challenges and Prospects. International Journal of Social Sciences and Public Administration, 2(3), 48-56.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
