# Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring

arXiv: https://arxiv.org/abs/2502.20748 · HTML: https://mlsanity.com/paper/2502.20748/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation](https://mlsanity.com/paper/2404.15845/) (2024)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Can Large Language Models Automatically Score Proficiency of Written Essays?](https://mlsanity.com/paper/2403.06149/) (2024)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [Automated essay scoring with string kernels and word embeddings](https://mlsanity.com/paper/1804.07954/) (2018)
- [Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays](https://mlsanity.com/paper/2102.00781/) (2021)
- [Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring](https://mlsanity.com/paper/2305.16826/) (2023)
- [Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs](https://mlsanity.com/paper/2410.14202/) (2024)
- [Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards](https://mlsanity.com/paper/2409.17472/) (2024)
- [Autoregressive Score Generation for Multi-trait Essay Scoring](https://mlsanity.com/paper/2403.08332/) (2024)

## Built on by (most cited first, 6 of 6)

- [FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback](https://mlsanity.com/paper/2601.04574/) (2026)
- [Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring](https://mlsanity.com/paper/2605.25731/) (2026)
- [SWIM: Student Writing Simulation via Proficiency-Conditioned Generation](https://mlsanity.com/paper/2609.03215/) (2026)
- [FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writing](https://mlsanity.com/paper/2511.22883/) (2025)
- [From Feature-Based Models to Generative AI: Validity Evidence for Constructed Response Scoring](https://mlsanity.com/paper/2603.19280/) (2026)
- [A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring](https://mlsanity.com/paper/2608.28407/) (2026)

## Abstract (arXiv)

Multi-trait automated essay scoring (AES) systems provide a fine-grained evaluation of an essay's diverse aspects. While they excel in scoring, prior systems fail to explain why specific trait scores are assigned. This lack of transparency leaves instructors and learners unconvinced of the AES outputs, hindering their practical use. To address this, we propose a self-explainable Rationale-Driven Multi-trait automated Essay scoring (RaDME) framework. RaDME leverages the reasoning capabilities of large language models (LLMs) by distilling them into a smaller yet effective scorer. This more manageable student model is optimized to sequentially generate a trait score followed by the corresponding rationale, thereby inherently learning to select a more justifiable score by considering the subsequent rationale during training. Our findings indicate that while LLMs underperform in direct AES tasks, they excel in rationale generation when provided with precise numerical scores. Thus, RaDME integrates the superior reasoning capacities of LLMs into the robust scoring accuracy of an optimized smaller model. Extensive experiments demonstrate that RaDME achieves both accurate and adequate reasoning while supporting high-quality multi-trait scoring, significantly enhancing the transparency of AES.