Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals
Published in ACL Anthology: Findings of EMNLP, 2024
While current Automated Essay Scoring (AES) methods demonstrate high scoring agreement with human raters, their decision-making mechanisms are not fully understood. Our proposed method, using counterfactual intervention assisted by Large Language Models (LLMs), reveals that BERT-like models primarily focus on sentence-level features, whereas LLMs such as GPT-3.5, GPT-4 and Llama-3 are sensitive to conventions & accuracy, language complexity, and organization, indicating a more comprehensive rationale alignment with scoring rubrics. Moreover, LLMs can discern counterfactual interventions when giving feedback on essays. Our approach improves understanding of neural AES methods and can also apply to other domains seeking transparency in model-driven decisions.
The source code of the project is available at GitHub.
Recommended citation: Yupei Wang, Renfen Hu, and Zhe Zhao. 2024. Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8906–8925, Miami, Florida, USA. Association for Computational Linguistics.
Download Paper | Download Slides