Multilingual Encoder + CJK-Only Queries Jumps MOOC-CS Hierarchical R@10 to 68.1
On MOOC-CS (), combining a multilingual dense encoder with CJK-only queries produces the language-matched control jump: flat-dense Recall@ rises to 49.2 [44.8, 53.6], the hierarchical baseline rises to 68.1 [62.1, 74.1], and Adaptive (heuristic) reaches 65.5 [58.6, 72.3]. The configuration is reported as a control rather than a strict-parity headline because both the encoder and query interface change relative to the default setup.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
Template Stripping on MOOC-CS Raises Hierarchical R@10 from 23.1 to 26.5 (MiniLM Encoder)
Multilingual Encoder Alone Does Not Improve MOOC-CS Recall (Hierarchical R@10 = 22.3 vs 23.1)
Multilingual Encoder + CJK-Only Queries Jumps MOOC-CS Hierarchical R@10 to 68.1
Graph Effect on MOOC-CS Is Conditional on Dense Seed Pool Quality
MiniLM Encoder + CJK-Only Queries on MOOC-CS: Hierarchical R@10 Rises from 23.1 to 26.5 with Flat Dense at 21.7
Multilingual Encoder + CJK-Only Queries Jumps MOOC-CS Hierarchical R@10 to 68.1
Template Stripping on MOOC-CS Raises Hierarchical R@10 from 23.1 to 26.5 (MiniLM Encoder)
Multilingual Encoder Alone Does Not Improve MOOC-CS Recall (Hierarchical R@10 = 22.3 vs 23.1)
MiniLM Encoder + CJK-Only Queries on MOOC-CS: Hierarchical R@10 Rises from 23.1 to 26.5 with Flat Dense at 21.7
Graph Effect on MOOC-CS Is Conditional on Dense Seed Pool Quality