al-folio

a simple whitespace theme for academics

The False Promise of Imitating Proprietary LLMs

논문 리뷰 - sLLM, LLM, Evaluation Metric 관련 연구

7 min read · June 22, 2023

2023 · evaluation metric gpt llm paper-review rlhf sllm · paper-reviews
Do Prompt-Based Models Really Understand the Meaning of Their Prompts?

논문 리뷰 - Instruction Tuning, ICL, Prompt Tuning 관련 연구

9 min read · June 15, 2023

2023 · bert fine-tuning gpt icl instruction tuning language-model nlp paper-review prompt tuning reasoning · paper-reviews
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

논문 리뷰 - LLM, ICL 관련 연구

13 min read · May 25, 2023

2023 · classification detection gpt icl language-model llm nlp paper-review · paper-reviews
Measuring Association Between Labels and Free-Text Rationales

논문 리뷰 - Reasoning 관련 연구

9 min read · May 11, 2023

2023 · embedding paper-review reasoning · paper-reviews
Automatic chain of thought prompting in large language models

논문 리뷰 - Prompt Tuning 관련 연구

1 min read · April 27, 2023

2023 · language-model paper-review prompt tuning · paper-reviews