# Confusion-Aware Rubric Optimization for LLM-based Automated Grading

arXiv: https://arxiv.org/abs/2603.00451 · HTML: https://mlsanity.com/paper/2603.00451/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs](https://mlsanity.com/paper/2503.10084/) (2025)
- [Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers](https://mlsanity.com/paper/2204.03503/) (2022)
- [A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization](https://mlsanity.com/paper/2410.02165/) (2024)
- [Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.05276/) (2025)

## Built on by (most cited first, 3 of 3)

- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges](https://mlsanity.com/paper/2605.26046/) (2026)
- [Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization](https://mlsanity.com/paper/2605.29274/) (2026)

## Abstract (arXiv)

Accurate and unambiguous guidelines are critical for large language model (LLM) based graders, yet manually crafting these prompts is often sub-optimal as LLMs can misinterpret expert guidelines or lack necessary domain specificity. Consequently, the field has moved toward automated prompt optimization to refine grading guidelines without the burden of manual trial and error. However, existing frameworks typically aggregate independent and unstructured error samples into a single update step, resulting in "rule dilution" where conflicting constraints weaken the model's grading logic. To address these limitations, we introduce Confusion-Aware Rubric Optimization (CARO), a novel framework that enhances accuracy and computational efficiency by structurally separating error signals. CARO leverages the confusion matrix to decompose monolithic error signals into distinct modes, allowing for the diagnosis and repair of specific misclassification patterns individually. By synthesizing targeted "fixing patches" for dominant error modes and employing a diversity-aware selection mechanism, the framework prevents guidance conflict and eliminates the need for resource-heavy nested refinement loops. Empirical evaluations on teacher education and STEM datasets demonstrate that CARO significantly outperforms existing SOTA methods. These results suggest that replacing mixed-error aggregation with surgical, mode-specific repair yields robust improvements in automated assessment scalability and precision.