人工智能反馈机制的必要性

这部分内容有帮助吗？

参考文献

Constitutional AI: Harmlessness from AI Feedback, Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, Jared Kaplan, 2022 arXiv preprint arXiv:2212.08073 DOI: 10.48550/arXiv.2212.08073 - 介绍了宪法式人工智能 (Constitutional AI)，这是一种利用人工智能定义的“宪法”和人工智能反馈来对齐大型语言模型与人类价值观的方法，适用于监督学习和强化学习，解决了人类可扩展性的局限。
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback, Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, Sushant Prakash, 2024 Proceedings of the 41st International Conference on Machine Learning, Vol. 235 (PMLR) DOI: 10.48550/arXiv.2309.00267 - 提出了基于人工智能反馈的强化学习 (RLAIF) 作为人类反馈强化学习 (RLHF) 的替代方案，展示了人工智能生成的偏好如何训练奖励模型，以更具可扩展性和高效性地对齐大型语言模型。
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena, Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, Ion Stoica, 2023 NeurIPS 2023 Datasets and Benchmarks Track DOI: 10.48550/arXiv.2306.05685 - 探讨了使用大型语言模型作为裁判来评估其他大型语言模型的可靠性和有效性，这是许多人工智能反馈机制的核心组成部分。