Problem
Research questions and friction points this paper is trying to address.
Multi-trait Automated Essay Scoring
rubric-grounded reasoning
structured feedback
score--feedback consistency
rubric alignment
A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
🤖 AI Summary
为了解决多特征自动评分中反馈与评分一致性差的问题，提出了一种统一框架HiFTS，通过生成层次化反馈并结合评分预测来提高评分准确性及反馈质量。
📝 Abstract
Multi-trait Automated Essay Scoring (AES) requires rubric-grounded reasoning across interdependent traits, rather than isolated score prediction. Existing feedback-enhanced methods often decouple feedback from scoring or assess traits independently, weakening score--feedback consistency and rubric alignment. We propose HiFTS, a unified autoregressive framework that generates hierarchical CoT feedback before predicting trait-level and holistic scores. HiFTS distills rubric-grounded hierarchical CoT feedback from a teacher LLM and trains student models to jointly generate feedback and scores. HiFTS further applies Group Relative Policy Optimization with a composite reward balancing score agreement, calibration, feedback quality, and structural validity. At inference, a lightweight global prior provides holistic guidance to reduce drift during long-form reasoning. We also introduce CFMS-34, a Chinese multi-trait AES dataset with 951 essays annotated with holistic scores and 34 rubric-based traits. Experiments on CFMS-34 and ASAP++ show that HiFTS achieves strong holistic and trait-level scoring while producing coherent, rubric-aligned feedback.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Unified Autoregressive Framework
Hierarchical CoT Feedback
Group Relative Policy Optimization
Composite Reward
🔎 Similar Papers
No similar papers found.
