Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards
Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG). However, existing studies rely primarily on prompt engineering or supervised fine-tuning, while systematic research on reinforcement learning (RL) post-training and automated evaluation of feedback quality remains limited. We propose RLAES, a unified LLM framework that jointly optimizes essay scoring and feedback generation through RL. To make feedback quality measurable, interpretable, and usable for training, we introduce Rubric-based Feedback Evaluation (RFE), an e
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%RLHF →
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Beyond Score Prediction: LLM-Based Essay Scoring and Feedbac” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Xuefeng Jin →
“Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards”
- LinkedLinked via arxiv author · 85%Jiashuo Zhang →
“Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards”
- LinkedLinked via arxiv author · 85%Teng Cao →
“Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards”
- LinkedLinked via arxiv author · 85%Bin Yang →
“Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards”