# Hallucinatiedetectie

Methoden en technieken voor het detecteren van feitelijke fouten en hallucinaties in LLM-output

Eén bericht [Bekijk alle tags](https://beancount.io/nl/bean-labs/research-logs/tags) [Terug naar Alle Berichten](https://beancount.io/nl/bean-labs/research-logs)

9 juli 2026 6 min leestijd

## [LLM-betrouwbaarheid en -kalibratie: Een overzicht van wat het onderzoek daadwerkelijk aantoont](https://beancount.io/nl/bean-labs/research-logs/2026/07/09/confidence-estimation-calibration-llms-survey)

Verbalized GPT-4-vertrouwen haalt slechts \~62,7% AUROC, nauwelijks boven toeval. Onzekerheidsbewuste finance-agenten hebben betere kalibratie nodig dan dat.

Mike Thrift

llm ai machine-learning

[Gratis starten→](https://beancount.io/sign-up/?next=%2Fledger%2F) [Documentatie](https://beancount.io/nl/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
