Caroline Wu

Margin- and Vocabulary-Aware Adaptive Retrieval for Industrial Technical Question Answering: A Controlled Pilot

Efficient industrial question answering requires reliable evidence retrieval despite document-specific terminology and spelling variation. We study confidence-gated dual retrieval (CGDR), which uses the normalized BM25 top-two margin to decide whether to invoke a complementary character n-gram index. On 80 held-out syn...