Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we use enhanced prompts throughout training by incorporating original prompt texts and trait descriptions, providing richer semantic information for trait-specific score generation. Experiments across multiple backbone models show that our 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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation
Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate poorly with human perception. We propos…
Reinforcement LearningVideo GenerationA Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
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…
Automated Essay ScoringAutoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback. Like typical AES systems, multi-trait AES employs the quadratic weighted kappa (QWK) to measu…
Automated Essay Scoringreinforcement-learningReinforcement LearningReinforcement Learning (RL)Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models
Automated essay scoring (AES) predicts multiple rubric-defined trait scores for each essay, where each trait follows an ordered discrete rating scale. Most LLM-based AES methods cast scoring as autoregressive token gener…
Automated Essay ScoringSTARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or r…
Lip Reading