GPT-31 InstructGPT : Training language models to follow instructions with human feedback 안녕하세요 모든 논문을 리뷰하기에는 너무 가내수공업이 많이 들고 그래서 짧게나마 제가 읽고 , 봤었던 논문에 대한 생각을 정리를 위해 Summary를 만들어보았습니다. https://openai.com/research/instruction-followinghttps://arxiv.org/abs/2203.02155 Training language models to follow instructions with human feedback Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs t.. 2024. 3. 6. 이전 1 다음
