Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about the threshold #3

Open
initzhang opened this issue Dec 2, 2024 · 0 comments
Open

Question about the threshold #3

initzhang opened this issue Dec 2, 2024 · 0 comments

Comments

@initzhang
Copy link

Hello team, thanks for this great work!

I am confused about the threshold value. As shown in the Equation 3 of the v4 version of paper, a negative value of $\Delta_{conf}^t$ signifies a reduced confidence in achieving a correct answer after step $t$. Therefore, an intuitive value for the process labeling threshold $\theta$ should be > 0, which implies that a good step makes the prediction closer to the ground truth. However, as discussed in Section 4.2.2, the threshold is set to $-0.5$ and experimented from $-0.5$ to $-0.9$ in the paper.

Could you explain why only negative $\theta$ is experimented in Table 5? Did you observe that most steps have negative $\Delta_{conf}^t$ during process labeling? Thank you!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant