Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 56 references that are in the map. First posted on arXiv 25 May 2026.
Builds on
26 of 56 references.
References · 26
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
- 2023Let's Verify Step by Stepcited by 3,789
- 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
- 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
- 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
- 2022Solving math word problems with process- and outcome-based feedbackcited by 901
- 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Modelscited by 96
- 2016Automatic Text Scoring Using Neural Networkscited by 51
- 2022On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representationcited by 46
14 more
- 2024Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoringcited by 33
- 2018Automated essay scoring with string kernels and word embeddingscited by 31
- 2025CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignmentcited by 26
- 2021Many Hands Make Light Work: Using Essay Traits to Automatically Score Essayscited by 25
- 2025GRPO-λ: Credit Assignment improves LLM Reasoningcited by 23
- 2024Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMscited by 22
- 2026Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoningcited by 19
- 2024Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewardscited by 12
- 2025TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoringcited by 12
- 2018Proximal Policy Optimization and its Dynamic Version for Sequence Generationcited by 7
- 2026DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignmentcited by 7
- 2025Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoringcited by 6
- 2024Transformer-based Joint Modelling for Automatic Essay Scoring and Off-Topic Detectioncited by 2
- 2026Enhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Trainingcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.