README
500 questions from Natural Questions used for the evaluation of confidence alignment in Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.
Source: Shuchang Tao et al, When to Trust LLMs: Aligning Confidence with Response Quality.
Contributors
mzhaoshuai
5 commits
nielsr
1 commits
Similar repos
README
500 questions from Natural Questions used for the evaluation of confidence alignment in Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.
Source: Shuchang Tao et al, When to Trust LLMs: Aligning Confidence with Response Quality.
Similar repos
Linked in READMEs
Contributors
mzhaoshuai
5 commits
nielsr
1 commits