LLM_apply

1.[LLM] TruthfulQA: Measuring How Models Mimic Human Falsehoods

post-thumbnail

저자: Stephanie Lin (Univ of Oxford), Jacob Hilton (OpenAI), Owain Evans (Univ of Oxford)연도: 2022제출: ACL 2022 main conference링크: https://arxiv.org/

2024년 4월 7일

2.[LLM] Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in LLMs

post-thumbnail

01. Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in LLMs >저자: Anonymous ACL submission 연도: 2023

2024년 4월 7일