TAPO improves autoregressive multi-trait essay scoring by decomposing rewards across samples and traits while using enhanced prompts, outperforming supervised fine-tuning and scalar-reward baselines.
In 9 Findings of the Association for Computational Lin- guistics: NAACL 2025, pages 2818–2824, Albu- querque, New Mexico
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
-
Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
TAPO improves autoregressive multi-trait essay scoring by decomposing rewards across samples and traits while using enhanced prompts, outperforming supervised fine-tuning and scalar-reward baselines.