Towards Self-Referential Analytic Assessment: A Profile-Based Approach to L2 Writing Evaluation with LLMs

TL;DR

This paper introduces a self-referential, profile-based evaluation framework for L2 writing assessment using LLMs, emphasizing intra-learner analysis over inter-learner ranking to better diagnose strengths and weaknesses.

Contribution

It proposes a novel intra-learner assessment method that improves diagnostic accuracy and compares LLMs with human raters in a zero-shot setting using a dense L2 writing dataset.

Findings

LLMs outperform single human raters in identifying weaknesses.

Human raters are better at recognizing strengths.

Rank-based metrics may obscure true diagnostic performance.

Abstract

Automated essay scoring (AES) research often relies on rank-based correlation metrics to validate analytic assessment. However, such metrics obscure both intrinsic intercorrelations among analytic dimensions that arise from the structure of writing proficiency itself and halo effects, whereby holistic impressions bleed into fine-grained component scores. As a result, high correlations may mask a system's true diagnostic behaviour. In this study, we propose a novel self-referential assessment evaluation framework that focuses on identifying intra-learner strengths and weaknesses rather than assessing inter-learner rankings. We conduct experiments on the publicly available ICNALE GRA, a uniquely dense second-language writing dataset annotated holistically and analytically by up to 80 trained raters. To obtain reliable reference scores, we apply two-facet Rasch modelling to calibrate rater severity and derive fair average scores across ten analytic aspects and holistic proficiency. We compare the analytic scoring performance of human operational raters and three large language models (LLMs) in a zero-shot setting. Our results show that LLMs tend to outperform single human raters in identifying relative weaknesses (negative feedback) across several proficiency aspects, while human raters remain stronger at identifying relative strengths (positive feedback). Overall, our findings highlight the limitations of rank-based evaluation for analytic assessment and demonstrate the value of intra-learner, profile-based methods for assessing and deploying LLMs in AES.