Tag
This paper proposes a cost-aware framework using a multi-armed bandit controller to adaptively select prompting strategies for LLM essay scoring, reducing LLM calls by 78.4% while maintaining accuracy.
ArguLens is an open-source system for automated essay scoring that uses fine-tuned LLMs for discourse classification, LightGBM for scoring, and a feedback generator to provide interpretable, label-aware results.
This paper introduces ICLE++, a new corpus of persuasive student essays annotated with both holistic and trait-specific scores, aimed at improving generalization and multi-trait scoring in automated essay scoring (AES) research.
This paper proposes RLAES, a unified LLM framework that jointly optimizes essay scoring and feedback generation via reinforcement learning with rubric-based rewards, achieving state-of-the-art scoring performance on the ASAP benchmark while maintaining high-quality feedback.
This paper proposes a generative AI-assisted summarization framework using GPT-5 model variants to address input-length limitations in automated essay scoring, demonstrating trade-offs between model capacity, summary fidelity, and computational cost on the ASAP 2.0 dataset.
This paper proposes a conditional generalizability framework to evaluate nonuniform dependability across response conditions in automated essay scoring.
Introduces a dataset of 32,534 double-marked GCSE student responses across five subjects, finding that top-performing LLMs agree with examiners more closely than examiners agree with each other, including on handwritten and subjective tasks.
This paper investigates sequential fine-tuning of LLaMA-3.1-8B for automated essay scoring using a curriculum aligned with discourse structure, showing improved coherence and performance compared to independent or randomized training.
This paper describes the development of an LLM-based tool using OpenAI's GPT models to evaluate approximately 1,200 Statements of Purpose for Purdue's SURF program, processing them in 4.6 hours and accelerating the review process compared to traditional human grading.