# Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring

arXiv: https://arxiv.org/abs/2502.08450 · HTML: https://mlsanity.com/paper/2502.08450/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [A Simple Recipe for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2106.03830/) (2021)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring](https://mlsanity.com/paper/2305.16826/) (2023)
- [Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring](https://mlsanity.com/paper/2008.01441/) (2020)
- [Automated Essay Scoring based on Two-Stage Learning](https://mlsanity.com/paper/1901.07744/) (2019)
- [Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards](https://mlsanity.com/paper/2409.17472/) (2024)
- [Key-Element-Informed sLLM Tuning for Document Summarization](https://mlsanity.com/paper/2406.04625/) (2024)
- [Neural Multi-task Learning in Automated Assessment](https://mlsanity.com/paper/1801.06830/) (2018)

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

- [The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring](https://mlsanity.com/paper/2606.10327/) (2026)

## Abstract (arXiv)

In automated essay scoring (AES), recent efforts have shifted toward cross-prompt settings that score essays on unseen prompts for practical applicability. However, prior methods trained with essay-score pairs of specific prompts pose challenges in obtaining prompt-generalized essay representation. In this work, we propose a grammar-aware cross-prompt trait scoring (GAPS), which internally captures prompt-independent syntactic aspects to learn generic essay representation. We acquire grammatical error-corrected information in essays via the grammar error correction technique and design the AES model to seamlessly integrate such information. By internally referring to both the corrected and the original essays, the model can focus on generic features during training. Empirical experiments validate our method's generalizability, showing remarkable improvements in prompt-independent and grammar-related traits. Furthermore, GAPS achieves notable QWK gains in the most challenging cross-prompt scenario, highlighting its strength in evaluating unseen prompts.