# Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

arXiv: https://arxiv.org/abs/2510.09030 · HTML: https://mlsanity.com/paper/2510.09030/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Checklists Are Better Than Reward Models For Aligning Language Models](https://mlsanity.com/paper/2507.18624/) (2025)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists](https://mlsanity.com/paper/2403.18771/) (2024)
- [HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition](https://mlsanity.com/paper/2402.15754/) (2024)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios](https://mlsanity.com/paper/2411.07037/) (2024)
- [Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?](https://mlsanity.com/paper/2508.15218/) (2025)
- [Large Language Models Are Active Critics in NLG Evaluation](https://mlsanity.com/paper/2410.10724/) (2024)
- [HPSS: Heuristic Prompting Strategy Search for LLM Evaluators](https://mlsanity.com/paper/2502.13031/) (2025)
- [Do We Need a Detailed Rubric for Automated Essay Scoring using Large Language Models?](https://mlsanity.com/paper/2505.01035/) (2025)

## Built on by (most cited first, 4 of 4)

- [Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality](https://mlsanity.com/paper/2607.03691/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring](https://mlsanity.com/paper/2608.28407/) (2026)
- [SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges](https://mlsanity.com/paper/2610.19992/) (2026)

## Abstract (arXiv)

The performance of Large Language Models (LLMs) is highly sensitive to the prompts they are given. Drawing inspiration from the field of prompt optimization, this study investigates the potential for enhancing Automated Essay Scoring (AES) by refining the scoring rubrics used by LLMs. Specifically, our approach prompts models to iteratively refine rubrics by reflecting on models' own scoring rationales and observed discrepancies with human scores on sample essays. Experiments on the TOEFL11 and ASAP datasets using GPT-4.1, Gemini-2.5-Pro, and Qwen-3-Next-80B-A3B-Instruct show Quadratic Weighted Kappa (QWK) improvements of up to 0.19 and 0.47, respectively. Notably, even with a simple initial rubric, our approach achieves comparable or better QWK than using detailed human-authored rubrics. Our findings highlight the importance of iterative rubric refinement in LLM-based AES to enhance alignment with human evaluations.