# EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading

arXiv: https://arxiv.org/abs/2606.06350 · HTML: https://mlsanity.com/paper/2606.06350/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 4 Jun 2026.

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

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [A Survey of Temporal Credit Assignment in Deep Reinforcement Learning](https://mlsanity.com/paper/2312.01072/) (2023)
- [Distilling ChatGPT for Explainable Automated Student Answer Assessment](https://mlsanity.com/paper/2305.12962/) (2023)
- [InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning](https://mlsanity.com/paper/2601.14209/) (2026)
- [Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring](https://mlsanity.com/paper/2406.19949/) (2024)
- [Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time](https://mlsanity.com/paper/2502.19230/) (2025)
- [DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment](https://mlsanity.com/paper/2605.03327/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)

## Abstract (arXiv)

Reliable rubric grading requires more than accurate score prediction. Each judgement must be grounded in the mark scheme and evidence from the student answer. Existing credit-assignment and intervention methods, primarily designed for self-contained reasoning tasks such as mathematics reasoning, struggle in this setting because they do not identify where grading reasoning goes wrong or how the model's belief about the final mark changes during reasoning. We propose Evidence-Diagnosed Intervention Training (EDIT), a two-phase framework for training more rubric-faithful LLM graders. First, EDIT-SFT locates problematic reasoning steps using internal model signals: posterior belief over the final mark and input-grounding scores. It then revises only these local steps with help from a rubric checklist. Second, EDIT-RL calibrates the grader with belief-guided reward shaping, penalising large harmful belief drifts while still allowing helpful exploration. Experiments on two real-world, multi-subject grading benchmarks demonstrate that EDIT consistently outperforms strong supervised fine-tuning and reinforcement learning baselines on both in-domain and out-of-domain splits, with ablation studies confirming that internal-state diagnostics drive these gains. Under deterministic rubric-edit interventions, EDIT-SFT is the most rule-responsive of all evaluated systems, and EDIT-RL largely retains this responsiveness while improving accuracy.