ANN search quality is better assessed by 1/Ratio@k than Recall@k because the former tracks downstream task utility more closely while allowing substantially lower computational cost.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Skills-aware RAG and multi-task learning approaches using a 33-skill dictionary significantly outperform baselines in classifying teachers' Van Hiele levels from 226 open-ended geometry responses.
citing papers explorer
-
ANN Search: Recall What Matters
ANN search quality is better assessed by 1/Ratio@k than Recall@k because the former tracks downstream task utility more closely while allowing substantially lower computational cost.
-
Automatically Inferring Teachers' Geometric Content Knowledge: A Skills Based Approach
Skills-aware RAG and multi-task learning approaches using a 33-skill dictionary significantly outperform baselines in classifying teachers' Van Hiele levels from 226 open-ended geometry responses.