SkinDeepRESEARCHSteve Seguin

Use case · Related prototype

Rank search results

Put useful matches near the top.

  1. Query and first matches
  2. Score relevance
  3. Return a ranked list
Illustration of the proposed workflow.

A knowledge base can show useful documents without generating an answer. A second scorer can reorder the first matches when word overlap alone gives a poor ranking.

Where the small model fits

A small model reads each query-document pair and returns a relevance score. An adaptive version could reserve a larger scorer for close calls, provided that deciding when to stop costs less than it saves.

What would need to work

Use held-out relevance judgments, ranking quality and total query time. The current reranker experiment is not evidence that early stopping preserves those rankings.

Related experiments and evidence