Automated Multiple Mini Interview (MMI) Scoring
This addresses the need for scalable and reliable automated assessment of soft skills in competitive selection processes, offering a novel alternative to data-intensive fine-tuning.
The paper tackled the problem of inconsistent and biased human scoring in Multiple Mini-Interviews (MMIs) by developing a multi-agent prompting framework for automated scoring, which outperformed fine-tuned baselines with an average QWK of 0.62 vs. 0.32 and achieved reliability comparable to human experts.
Assessing soft skills such as empathy, ethical judgment, and communication is essential in competitive selection processes, yet human scoring is often inconsistent and biased. While Large Language Models (LLMs) have improved Automated Essay Scoring (AES), we show that state-of-the-art rationale-based fine-tuning methods struggle with the abstract, context-dependent nature of Multiple Mini-Interviews (MMIs), missing the implicit signals embedded in candidate narratives. We introduce a multi-agent prompting framework that breaks down the evaluation process into transcript refinement and criterion-specific scoring. Using 3-shot in-context learning with a large instruct-tuned model, our approach outperforms specialised fine-tuned baselines (Avg QWK 0.62 vs 0.32) and achieves reliability comparable to human experts. We further demonstrate the generalisability of our framework on the ASAP benchmark, where it rivals domain-specific state-of-the-art models without additional training. These findings suggest that for complex, subjective reasoning tasks, structured prompt engineering may offer a scalable alternative to data-intensive fine-tuning, altering how LLMs can be applied to automated assessment.