Tag
PhoenixNest-Video introduces an evidence-grounded multimodal agent framework for automated video interview assessment, achieving 91.50% grade-level accuracy on a benchmark by using structured video graphs and reinforcement learning.
This paper presents an interpretable feature-LLM hybrid system for automated L2 English speaking assessment that outperforms individual human raters and shows that pause encoding does not significantly impact LLM fluency scores.
The article describes the architecture of KeplerCrew, an AI coding agent that automates output scoring before PR submission, highlighting challenges in plan sequencing, cost predictability, and air-gapped deployment.
This paper proposes learning assessment skills for LLMs to automate rubric construction for scoring tasks, achieving performance comparable to expert-written rubrics without requiring human-written examples.
This study analyzes how modifications to evaluation rubrics, such as shifting from holistic to analytic criteria, impact the agreement between human raters and AI autoraters. The findings suggest that providing examples and reducing bias improves agreement, while higher complexity tends to decrease it.
This paper presents a hybrid framework for detecting alarming or distressed student verbal responses by combining a text classifier (content-based) and an audio classifier (prosodic features), aimed at expediting human review in Automated Verbal Response Scoring systems. The approach addresses a safety gap in automated scoring pipelines where at-risk student responses may otherwise go unnoticed.