Natural Language-based Assessment of L2 Oral Proficiency using LLMs
This work addresses the need for automated, interpretable language assessment tools for language learners, though it is incremental as it builds on existing LLM capabilities.
The study tackled the problem of assessing second language oral proficiency by using large language models (LLMs) to interpret can-do descriptors in a zero-shot setting, achieving competitive performance that surpassed a BERT-based model but did not outperform fine-tuned speech LLMs.
Natural language-based assessment (NLA) is an approach to second language assessment that uses instructions - expressed in the form of can-do descriptors - originally intended for human examiners, aiming to determine whether large language models (LLMs) can interpret and apply them in ways comparable to human assessment. In this work, we explore the use of such descriptors with an open-source LLM, Qwen 2.5 72B, to assess responses from the publicly available S&I Corpus in a zero-shot setting. Our results show that this approach - relying solely on textual information - achieves competitive performance: while it does not outperform state-of-the-art speech LLMs fine-tuned for the task, it surpasses a BERT-based model trained specifically for this purpose. NLA proves particularly effective in mismatched task settings, is generalisable to other data types and languages, and offers greater interpretability, as it is grounded in clearly explainable, widely applicable language descriptors.