The wiki's advantage over vector RAG is roughly three times larger on cross-page questions than on topic-page questions, in both score and groundedness¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Splitting 59 questions by class, the wiki arm was nearly indifferent to question class (9.96 vs. 9.93 score) while vector RAG dropped from 9.33 on topic-page to 8.14 on cross-page questions, widening the score gap from 0.62 to 1.79 points and the groundedness gap from 87% vs. 98% to 64% vs. 100%. → Brian Wright 2026

Evidence¶

Brian Wright 2026¶

Brian Wright. (2026). Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing. https://arxiv.org/abs/2609.25303 doi:10.48550/arxiv.2609.25303

q2 · i? · causal · r2

Question-class split of the same head-to-head evaluation (45 topic-page and 14 cross-page questions). The article reports the wiki arm "nearly indifferent to question class" at 9.96 vs. 9.93, while RAG's gap widened to 1.79 on cross-page questions with groundedness falling to 64% vs. 100%.

"vector RAG is not (9.33 vs. 8.14 score, an 0.62 point gap on topic page [95% CI on the gap: 0.16, 1.18] widening to 1.79 oncrosspage[95%CI:0.57,3.14];87%vs.64%grounded)"

Discussion¶

Related Claims¶

• The topic-page groundedness gap between wiki and vector RAG was the study's only comparison not reaching significance at the 95% level — related
• Retrieval failure explained only 2 of vector RAG's 11 ungrounded answers; 9 answers retrieved the correct material and were still ungrounded, suggesting chunked context invites fabrication — related