informatique:ai_lm:ai_nlp_rag
Différences
Ci-dessous, les différences entre deux révisions de la page.
| Les deux révisions précédentesRévision précédente | |||
| informatique:ai_lm:ai_nlp_rag [04/06/2026 08:18] – [AI NLP and RAG] cyrille | informatique:ai_lm:ai_nlp_rag [04/06/2026 08:21] (Version actuelle) – [AI NLP and RAG] cyrille | ||
|---|---|---|---|
| Ligne 37: | Ligne 37: | ||
| - Step-Back Prompting -- LLM generates a more abstract query; both queries used for retrieval across all tree levels | - Step-Back Prompting -- LLM generates a more abstract query; both queries used for retrieval across all tree levels | ||
| - Confidence-Gated Adaptive Depth -- retrieval starts at leaf level, ascends tree only if confidence is below threshold | - Confidence-Gated Adaptive Depth -- retrieval starts at leaf level, ascends tree only if confidence is below threshold | ||
| + | |||
| + | < | ||
| + | query | ||
| + | → multi-query expansion (2 rewrites + 1 step-back, via LLM) | ||
| + | → hybrid retrieval per variant (BM25 + dense + RRF, top-20 each) | ||
| + | → RRF merge across all variants | ||
| + | → cross-encoder rerank (top-50 → top-5) | ||
| + | → context compression (sentence-level filtering by cosine sim to query, | ||
| + | keep top 12 sentences, collapse into one chunk) | ||
| + | → LLM with short-answer prompt | ||
| + | </ | ||
| + | |||
| Articles | Articles | ||
informatique/ai_lm/ai_nlp_rag.txt · Dernière modification : de cyrille