# Génération augmentée par récupération

Techniques RAG pour ancrer les sorties des modèles de langage dans les documents financiers et les données de grand livre

Un article [Voir tous les tags](https://beancount.io/fr/bean-labs/research-logs/tags) [Retour à tous les articles](https://beancount.io/fr/bean-labs/research-logs)

18 mai 2026 7 minutes de lecture

## [FLARE : Génération augmentée par récupération active](https://beancount.io/fr/bean-labs/research-logs/2026/05/18/flare-active-retrieval-augmented-generation)

FLARE atteint 51,0 EM sur 2WikiMultihopQA contre 39,4 pour le RAG à récupération unique, mais les échecs de calibration en chat limitent son usage pour les agents finance.

Mike Thrift

ai machine-learning llm

[Commencer gratuitement→](https://beancount.io/sign-up/?next=%2Fledger%2F) [Documentation](https://beancount.io/fr/docs)

## Where to look next

- [Sitemap](https://beancount.io/sitemap.xml) - all pages with hreflang alternates
- [LLMs index](https://beancount.io/llms.txt) - curated links for AI agents (also /llms-full.txt for full docs)
- [Documentation](https://beancount.io/docs) - every doc is also available as text/markdown via .md suffix or Accept negotiation
- [REST API reference](https://beancount.io/docs/api-reference) - interactive endpoints, schemas, authentication, and code samples
- [OpenAPI spec](https://beancount.io/openapi.json) - OpenAPI 3.1 spec for this website's public content endpoints; the product contract for ledger operations is at https://beancount.io/api-gateway/v1/openapi.json
- [GraphQL](https://beancount.io/graphql) - public, read-only content API over the blog and research logs (no credentials, no ledger data): 12 query fields over 23 types
- [MCP server](https://beancount.io/mcp) - Model Context Protocol at https://beancount.io/api-gateway/mcp
