SOURCE-LINKED INTELLIGENCE

Rubric-Aligned Disentangled Evaluation of Human Simultaneous Interpreting

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Human simultaneous interpreting (SI) is commonly assessed with analytic rubrics separating meaning transfer, delivery quality, and temporal synchrony, yet no automatic metric is designed for rubric-aligned segment-level SI evaluation. We construct a professionally annotated corpus of 1,101 SI segments with scores for meaning transfer (LQ), delivery quality (EXP), and perceived latency (LAT). We show that structured LLM prompting and scalar supervision collapse rubric dimensions, yielding near-zero correlation with human ratings and strong cross-dimension coupling. To isolate supervision struct

Read original source ↗ Open in workspace

recordType

paper

region

Global