Daniel Baumartz, Alexander Mehler, Mevlüt Bagci, Maxim Konca
原文摘要
Automated essay scorers (AES) based on large language models (LLMs) promise human-level accuracy. However, training, fine-tuning, and evaluating LLMs for specific assessment tasks is costly. In particular, the question arises whether these AES should be trained for specific domains or whether models based on generic LLMs might be sufficient. Human annotations, by contrast, are often more valid but far more expensive. This study evaluates whether ensembles of AES systems based on general-purpose LLMs can approximate human ratings of medical-education writing tasks by leveraging encoded linguistic and conceptual knowledge. The goal is to assess whether general-purpose models are applicable for assisting or potentially replacing human annotation in this domain. We experiment with 11 AES systems and 8 different LLMs and evaluate 668 student responses to 12 tasks, using \numprint{2076} evaluations by 7 human annotators. These ratings are aggregated to create consistent performance levels that can be used as target classes for classifiers trained on AES outputs. Our results show that learner classes based on human ratings can be accurately reconstructed using a linear SVM trained on a small set of AES features. A single classifier generalized well across tasks and domains, with reasoning and content features being most predictive. This suggests that out-of-the-box LLMs, even without domain-specific fine-tuning, can support automatic essay grading in medical education. While individual AES systems are insufficient alone, their combination approximates human evaluators, pointing to a reduced need for manual scoring or its supplementation with automated methods.
Digital assessment traces are increasingly used to predict student performance, often evaluated by correlating predicted and observed scores pooled across tasks. However, such correlations may reflect between-task differences rather than performance differences among students within tasks. To investigate this, we analyzed up to 527 browsing sessions from 424 university students completing open-Internet Critical Online Reasoning tasks and assessed the cross-task stability of their ratings. We evaluated the same out-of-fold predictions within and across tasks, compared three validation tiers up to leave-one-task-out, and tested incremental predictive contributions of consultation order and relational structure against matched permutation and randomization controls. None of the twelve prespecified primary tests was significant: on held-out tasks, consulted-page features showed no significant association with relative student performance, nor did observed order or relational structure add predictive value. Pooling observations across tasks substantially increased correlations, particularly for factual correctness, whose scores showed limited evidence of stable between-student differences across tasks. However, sentence embeddings yielded modest positive correlations with generic response quality on held-out tasks, without establishing added predictive value from observed order or relational structure. Our findings show that pooled predictive correlations may not reflect within-task student differences, highlighting the need for within-task evaluation and criterion generalizability audits.