Author

Yunfang Wu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... May 2026

Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring

Experiments show that the proposed Trait-Aware Policy Optimization method consistently improves multi-trait scoring performance over supervised fine-tuning and scalar-reward optimization baselines, demonstrating the effectiveness and transferability of trait-aware post-training for essay scoring.

Zhengyang Wang, Sanwoo Lee, Jiaxin Wang et al. · arXiv.org · 2 citations

#natural language process... Preprint Aug 2026

A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring

HiFTS is proposed, a unified autoregressive framework that generates hierarchical CoT feedback before predicting trait-level and holistic scores and applies Group Relative Policy Optimization with a composite reward balancing score agreement, calibration, feedback quality, and structural validity.

Shi-Hang Yang, Sanwoo Lee, Ning-Ning Zhao et al. · 1 citation