You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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!
The text was updated successfully, but these errors were encountered: