Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
An information-weighted cross-entropy loss that rescales token-level contributions using TF-IDF statistics, emphasizing semantically informative tokens while down-weighting ubiquitous ones is presented, offering a lightweight and principled way to mitigate memorization without disrupting standard training dynamics.
Fixing label errors in RVL-CDIP can enhance model performance by over 8 percentage points, but removing test-train duplicates may paradoxically hurt accuracy.
