Prompting Large Language Models for Zero-shot Essay Scoring via Multi-trait Specialization

arXiv:2404.04941v1 Announce Type: new
Abstract: Advances in automated essay scoring (AES) have traditionally relied on labeled essays, requiring tremendous cost and expertise for their acquisition. Recently, large language models (LLMs) have achieved great success in various tasks, but their potential is less explored in AES. In this paper, we propose Multi Trait Specialization (MTS), a zero-shot prompting framework to elicit essay scoring capabilities in LLMs. Specifically, we leverage ChatGPT to decompose writing proficiency into distinct traits and generate scoring criteria …

abstract acquisition advances arxiv automated cost cs.cl essay expertise language language models large language large language models llms paper prompting scoring success tasks type via zero-shot