Responsible Use of Large Language Models for Response Grading and Explanations in Structured Interviews

This research explores the responsible use of Large Language Models (LLMs) for automatic grading and explanation of interview responses. It highlights the potential of LLMs, such as GPT-4 and LLaMA-2, in enhancing interview assessments while emphasising the importance of avoiding biases. The study shows how adapting these models with targeted interview data can lead to more accurate and fair outcomes.