Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector (2403.09125v5)
Abstract: LLMs as chatbots have drawn remarkable attention thanks to their versatile capability in natural language processing as well as in a wide range of tasks. While there has been great enthusiasm towards adopting such foundational model-based artificial intelligence tools in all sectors possible, the capabilities and limitations of such LLMs in improving the operation of the electric energy sector need to be explored, and this article identifies fruitful directions in this regard. Key future research directions include data collection systems for fine-tuning LLMs, embedding power system-specific tools in the LLMs, and retrieval augmented generation (RAG)-based knowledge pool to improve the quality of LLM responses and LLMs in safety-critical use cases.
- “Attention is all you need” In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17 Long Beach, California, USA: Curran Associates Inc., 2017, pp. 6000–6010 URL: https://dl.acm.org/doi/10.5555/3295222.3295349
- “Improving Language Understanding by Generative Pre-Training” In OpenAI, 2018 URL: https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf
- “Large Foundation Models for Power Systems” In arXiv, 2023 URL: https://doi.org/10.48550/arXiv.2312.07044
- “On the Potential of ChatGPT to Generate Distribution Systems for Load Flow Studies Using OpenDSS” In IEEE Trans. Power Syst. 38.6, 2023, pp. 5965–5968 DOI: 10.1109/TPWRS.2023.3315543
- “Real-Time Optimal Power Flow With Linguistic Stipulations: Integrating GPT-Agent and Deep Reinforcement Learning” In IEEE Trans. Power Syst. 39.2, 2024, pp. 4747–4750 DOI: 10.1109/TPWRS.2023.3338961
- “Data Governance in the Age of Large-Scale Data-Driven Language Technology” In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’22 Seoul, Republic of Korea: Association for Computing Machinery, 2022, pp. 2206–2222 URL: https://doi.org/10.1145/3531146.3534637
- “Privacy in Large Language Models: Attacks, Defenses and Future Directions” In arXiv, 2023 URL: https://doi.org/10.48550/arXiv.2310.10383
- “A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation” In arXiv, 2023 URL: https://doi.org/10.48550/arXiv.2305.11391
- OpenAI “Enterprise Privacy at OpenAI” Accessed: 13/03/2024, 2023 URL: https://openai.com/enterprise-privacy
- “What’s in the chatterbox? Large language models, why they matter, and what we should do about them”, 2022 URL: https://stpp.fordschool.umich.edu/research/research-report/whats-in-the-chatterbox
- “NIST AI Risk Management Framework” URL: https://www.nist.gov/itl/ai-risk-management-framework
- “From Understanding to Utilization: A Survey on Explainability for Large Language Models” In arXiv, 2024 URL: https://doi.org/10.48550/arXiv.2401.12874
- “Learning unsupervised world models for autonomous driving via discrete diffusion” In arXiv, 2023 URL: https://doi.org/10.48550/arXiv.2311.01017
- “A survey on large language model (llm) security and privacy: The good, the bad, and the ugly” In High-Confidence Computing Elsevier, 2024, pp. 100211 DOI: https://doi.org/10.1016/j.hcc.2024.100211
- Lin Dong (17 papers)
- Subir Majumder (7 papers)
- Fatemeh Doudi (3 papers)
- Yuting Cai (4 papers)
- Chao Tian (78 papers)
- Dileep Kalathi (1 paper)
- Kevin Ding (1 paper)
- Anupam A. Thatte (2 papers)
- Le Xie (74 papers)
- Na Li (227 papers)