因此,香港浸会大学与 MBZUAI、卡内基梅隆大学、香港中文大学、悉尼大学以及墨尔本大学合作发表论文《Discovery of the Hidden World with Large Language Models》,提出了一个名为 COAT 的新型框架,旨在利用大型语言模型和因果发现方法的优势,突破传统因果发现方法的局限性,更有效地在现实世界中定义高级变量、理解因果关系。
论文已在 NeurIPS 2024 发表:论文标题:Discovery of the Hidden World with Large Language Models
@inproceedings{causalcoat2024, title={Discovery of the Hidden World with Large Language Models}, author={Chenxi Liu and Yongqiang Chen and Tongliang Liu and Mingming Gong and James Cheng and Bo Han and Kun Zhang}, year={2024}, booktitle={Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems} }
参考文献
[1] Norwood Russell Hanson. Patterns of discovery : an inquiry into the conceptual foundations of science. Cambridge University Press, 1958.
[2] Thomas S. Kuhn and David Hawkins. The structure of scientific revolutions. American Journal of Physics, 31:554–555, 1963.
[3] Peter Spirtes, Clark Glymour, and Richard Scheines. Causation, Prediction, and Search, Second Edition. Adaptive computation and machine learning. MIT Press, 2000.
[4] Peter Spirtes, Clark Glymour, Richard Scheines, and Robert Tillman. Automated Search for Causal Relations: Theory and Practice, 2018.
[5] Matthew J. Vowels, Necati Cihan Camgoz, and Richard Bowden. D’ya like dags? a survey on structure learning and causal discovery. ACM Computing Survey, 55(4), 2022.
[6] Bernhard Scholkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, and Yoshua Bengio. Towards causal representation learning. arXiv preprint, arXiv:2102.11107, 2021.
[7] Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In Advances in Neural Information Processing Systems, 2020.
[9] Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothee Lacroix, Baptiste Rozi `ere, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. Llama: Open and efficient foundation language models. arXiv preprint, arXiv:2302.13971, 2023.
[10] OpenAI. Gpt-4 technical report, 2023.
[11] Emre Kiciman, Robert Ness, Amit Sharma, and Chenhao Tan. Causal reasoning and large language models: Opening a new frontier for causality. arXiv preprint, arXiv:2305.00050, 2023.
[12] Sebastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, EceKamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott M. Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. Sparks of artificial general intelligence: Early experiments with GPT-4. arXiv preprint, arXiv:2303.12712, 2023.
[13] Cheng Zhang, Stefan Bauer, Paul Bennett, Jiangfeng Gao, Wenbo Gong, Agrin Hilmkil, Joel Jennings, Chao Ma, Tom Minka, Nick Pawlowski, and James Vaughan. Understanding causality with large language models: Feasibility and opportunities. arXiv preprint, arXiv:2304.05524, 2023.
[14] Ahmed Abdulaal, adamos hadjivasiliou, Nina Montana-Brown, Tiantian He, Ayodeji Ijishakin, Ivana Drobnjak, Daniel C. Castro, and Daniel C. Alexander. Causal modelling agents: Causal graph discovery through synergising metadata- and data-driven reasoning. In The Twelfth International Conference on Learning Representations, 2024.
[15] Matej Zecevic, Moritz Willig, Devendra Singh Dhami, and Kristian Kersting. Causal parrots: Large language models may talk causality but are not causal. Transactions on Machine Learning Research, 2023.
[16] Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng LYU, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, and Bernhard Sch ̈olkopf. CLadder: A benchmark to assess causal reasoning capabilities of language models. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
[17] Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona T. Diab, and Bernhard Sch ̈olkopf. Can large language models infer causation from correlation? arXiv preprint, arXiv:2306.05836, 2023.
[18] Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. Siren’s song in the AI ocean: A survey on hallucination in large language models. arXiv preprint, arXiv:2309.01219, 2023.
[19] Chenhang Cui, Yiyang Zhou, Xinyu Yang, Shirley Wu, Linjun Zhang, James Zou, and Huaxiu Yao. Holistic analysis of hallucination in gpt-4v(ision): Bias and interference challenges. arXiv preprint, arXiv:2311.03287, 2023.
[20] Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans. The reversal curse: Llms trained on ”a is b” fail to learn ”b is a”. arXiv preprint, arXiv:2309.12288, 2023.
[21] Constantin F. Aliferis, Alexander Statnikov, Ioannis Tsamardinos, Subramani Mani, and Xenofon D. Koutsoukos. Local causal and markov blanket induction for causal discovery and feature selection for classification part i: Algorithms and empirical evaluation. Journal of Machine Learning Research, 11(7):171–234, 2010.
[22] Shantanu Gupta, David Childers, and Zachary Chase Lipton. Local causal discovery for estimating causal effects. In Conference on Causal Learning and Reasoning, volume 213, pages 408–447, 2023.
[23] Judea Pearl and Dana Mackenzie. The Book of Why: The New Science of Cause and Effect. Basic Books, Inc., USA, 1st edition, 2018.
[24] Timo Schick, Jane Dwivedi-Yu, Roberto Dess`ı, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. arXiv preprint, arXiv:2302.04761, 2023.
[25] Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, Xuanjing Huan, and Tao Gui. The rise and potential of large language model based agents: A survey. arXiv preprint, arXiv:2309.07864, 2023.
[26] Ruibo Tu, Kun Zhang, Bo C. Bertilson, Hedvig Kjellstrom, and Cheng Zhang. Neuropathic pain diagnosis simulator for causal discovery algorithm evaluation. In Advances in Neural Information Processing Systems, pages 12773–12784, 2019.
[39] Gilbert P Compo, Jeffrey S Whitaker, Prashant D Sardeshmukh, Nobuki Matsui, Robert J Allan, Xungang Yin, Byron E Gleason, Russell S Vose, Glenn Rutledge, Pierre Bessemoulin, et al. The twentieth century reanalysis project. Quarterly Journal of the Royal Meteorological Society, 137(654):1–28, 2011.
[40] Jakob Bjerknes. Atmospheric teleconnections from the equatorial pacific. Monthly weather review, 97(3):163–172, 1969.
[41] Chunzai Wang. Enso, atlantic climate variability, and the walker and hadley circulations. In The Hadley circulation: Present, past and future, pages 173–202. Springer, 2004.
[42] Yinge Liu, Ninglian Wang, Lingang Wang, Zhongming Guo, and Xiaobo Wu. Variation of cloud amount over china and the relationship with enso from 1951 to 2014. International Journal of Climatology, 36(8):2931–2941, 2016.
[43] Anoop Kumar Mishra. Investigating changes in cloud cover using the long-term record of precipitation extremes. Meteorological Applications, 26(1):108–116, 2019.