EdTech Tracker

← Coding lens

cross encoder

architecture judged 100% likely a named technique or architecture

First seen
2024-04-11
Independent sources
8
Articles
22
Last 4 weeks vs prior
0 vs 6

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
0242024-W152026-W182026-W41
Table view
WeekArticlesSources
2024-W1511
2024-W2211
2024-W2411
2024-W2611
2024-W3311
2026-W0921
2026-W1141
2026-W1811
2026-W2411
2026-W3311
2026-W3511
2026-W3611
2026-W4042
2026-W4121

In their words

get ( " rerank_score " , r [ " score " ]), rank = i ) for i , r in enumerate ( final ) ] # Cross-encoder reranker (best quality) from sentence_transformers import CrossEncoder reranker_model = CrossEncoder ( " cross-encoder/ms-marco-MiniLM-L-6-v2 " ) def rerank ( query : str , documents : List [ str ]) -> List [ float ]: pairs = [( query , doc ) for doc in documents ] scores = reranker_model .

Map each candidate to the kind of specialist model that fits it: a small generative model or a trained classifier for page types, a zero-shot entity model such as GLiNER2 or NuNER_Zero for entity tagging, a cross-encoder reranker in place of an LLM asked "is this chunk relevant?", and a document model plus a structured-output model for table fields.

After retrieval Reranking: Retrieve a generous candidate set (say 30 to 50), then rescore it with a cross-encoder or reranking model that reads the query and each passage together.

A cross-encoder reranker for the final relevance call.

Run both, then rerank with a cross-encoder.

On top of that sits a cross-encoder reranker: a second-pass model that looks at the actual query and each candidate passage together, rather than comparing pre-computed embeddings in isolation.

Then a cross-encoder reranker reads the query and each candidate together, producing a much sharper relevance score by attending across both texts at once.

A query combines vector and BM25 search, fuses their rankings, reranks the candidates with a cross-encoder, reweights them by recency, and attaches neighboring chunks.