Naive concatenation of demographic metadata to text input in a DistilBERT AES model reduces QWK from 0.727 to 0.656, raises validation loss, and lowers score parity instances from 15 to 12 on the ASAP 2.0 dataset via 10-fold cross-validation.
ASAP 2.0: Automated Student Assessment Prize,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Demographic Metadata as Construct-Irrelevant Noise in DistilBERT-Based Automated Essay Scoring
Naive concatenation of demographic metadata to text input in a DistilBERT AES model reduces QWK from 0.727 to 0.656, raises validation loss, and lowers score parity instances from 15 to 12 on the ASAP 2.0 dataset via 10-fold cross-validation.