[NLP] (NeurlPS'23) Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
사람의 사고 과정을 그대로 모방하여 복잡한 문제를 자연어처리를 통해 풀게끔 하는 방법론인 Chain-of-Thought이라는 연구입니다. 읽은 날짜 2023.06.04 카테고리 #자연어처리논문리뷰, #프롬프트, #Chain-of-Thought Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Authors: Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, Denny Zhou DOI: https://arxiv.org/abs/2201.11903 Keywords: Issue Date: Publisher: 2023 ..
더보기
[NLP] (EMNLP 2022) RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
optimal 한 prompt를 찾는 태스크에 강화학습을 적용한 연구 입니다. 읽은 날짜 2023.05.30 카테고리 #자연어처리논문리뷰, #프롬프트, #강화학습 RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning Authors: Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric Xing, Zhiting Hu DOI: https://aclanthology.org/2022.emnlp-main.222/ Keywords: Issue Date: December 2022 Publisher: EMNLP 2022 1. 등장 ..
더보기