Principle-driven self-alignment of language models from scratch with minimal human supervision
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
Principle-driven self-alignment of language models from scratch with minimal human supervision
Z Sun, Y Shen, Q Zhou, H Zhang, Z Chen… - Proceedings of the 37th …, 2023 - dl.acm.org
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
[引用][C] Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun - cs.cmu.edu
publications | Zhiqing Sun Zhiqing Sun Toggle navigation about publications(current)
publications For a more up-to-date list, please also check the google scholar page. 2023 1.NeurIPS …
publications For a more up-to-date list, please also check the google scholar page. 2023 1.NeurIPS …
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun, Y Shen, Q Zhou, H Zhang… - Advances in …, 2023 - proceedings.neurips.cc
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun, Y Shen, Q Zhou, H Zhang, Z Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun, Y Shen, Q Zhou, H Zhang, Z Chen… - … -seventh Conference on … - openreview.net
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun, Y Shen, Q Zhou, H Zhang, Z Chen… - Annual Conference …, 2023 - research.ibm.com
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Z Sun, Y Shen, Q Zhou, H Zhang, Z Chen… - arXiv e …, 2023 - ui.adsabs.harvard.edu
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …
(SFT) with human annotations and reinforcement learning from human feedback (RLHF) to …