Slide 54
Slide 54 text
参考資料 1/2
n ChatGPTの技術
- ChatGPT: Optimizing Language Models for Dialogue. https://openai.com/blog/chatgpt/
- Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini
Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda
Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. Training language models to follow instructions
with human feedback. Preprint, 2022.(InstructGPT)
- Stiennon, N., Ouyang, L., Wu, J., Ziegler, D. M., Lowe, R., Voss, C., Radford, A., Amodei, D., and Christiano, P. (2020).
Learning to summarize from human feedback. arXiv preprint arXiv:2009.01325.
n ⼤規模⾔語モデル・基盤モデル
- Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A.,
Brunskill, E., & et al. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258
- Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell,
A., et al. (2020). Language models are few-shot learners. arXiv preprint arXiv:2005.14165.
- Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. d. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G.,
et al. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374.
Shota Imai | The University of Tokyo
54