# Откриване на измами

Откриване на аномални или измамни записи във финансови данни

7 публикации [Вижте всички етикети](https://beancount.io/bg/bean-labs/research-logs/tags) [Обратно към всички публикации](https://beancount.io/bg/bean-labs/research-logs)

3 юли 2026 г. 5 минути четене

## [LLM Anomaly Detection Survey (NAACL 2025): Strong Taxonomy, Absent Tabular Coverage](https://beancount.io/bg/bean-labs/research-logs/2026/07/03/llm-anomaly-ood-detection-survey)

The NAACL 2025 taxonomy holds, but tabular coverage is absent. Finance AI teams must adapt vision-model methods themselves.

Mike Thrift

ai llm machine-learning

26 юни 2026 г. 6 минути четене

## [AD-LLM Benchmark: GPT-4o Hits 0.93+ AUROC Zero-Shot for Text Anomaly Detection](https://beancount.io/bg/bean-labs/research-logs/2026/06/26/ad-llm-benchmarking-llms-anomaly-detection)

AD-LLM finds GPT-4o hits 0.93–0.99 AUROC zero-shot for text anomaly detection, but LLM model selection stays unreliable for financial audit AI.

Mike Thrift

llm ai machine-learning

25 юни 2026 г. 6 минути четене

## [CausalTAD: Causal Column Ordering for LLM Tabular Anomaly Detection](https://beancount.io/bg/bean-labs/research-logs/2026/06/25/causaltad-causal-knowledge-llm-tabular-anomaly-detection)

CausalTAD reorders table columns by causal dependency before LLM serialization, raising average AUC-ROC from 0.803 to 0.834 over AnoLLM.

Mike Thrift

llm ai machine-learning

24 юни 2026 г. 6 минути четене

## [AnoLLM: Fine-Tuning LLMs for Tabular Anomaly Detection in Financial Data](https://beancount.io/bg/bean-labs/research-logs/2026/06/24/anollm-llm-fine-tuning-tabular-anomaly-detection)

AnoLLM beats classical baselines on mixed-type fraud data by scoring rows with LLM negative log-likelihood, but adds no edge on purely numerical tables.

Mike Thrift

ai llm machine-learning

21 юни 2026 г. 6 минути четене

## [Zero-Shot Anomaly Detection with LLMs: How GPT-4 Performs on Tabular Data](https://beancount.io/bg/bean-labs/research-logs/2026/06/21/anomaly-detection-tabular-data-llms)

GPT-4 reaches 74.1 mean AUROC on ODDS zero-shot, near the 75.5 ECOD baseline, but fails on high-variance data. Ledger auditing is not solved yet.

Mike Thrift

ai llm fraud-detection

22 май 2026 г. 6 минути четене

## [AuditCopilot: LLMs for Fraud Detection in Double-Entry Bookkeeping](https://beancount.io/bg/bean-labs/research-logs/2026/05/22/auditcopilot-llm-fraud-detection-double-entry-bookkeeping)

AuditCopilot cuts journal entry fraud false positives from 942 to 12, but ablation shows the LLM mainly synthesizes Isolation Forest scores.

Mike Thrift

fraud-detection llm double-entry

20 април 2026 г. 5 минути четене

## [Chain-of-Thought Prompting: Компромиси между точност и пълнота за AI във финансите](https://beancount.io/bg/bean-labs/research-logs/2026/04/20/chain-of-thought-prompting-reasoning-tradeoffs)

Chain-of-Thought повишава прецизността, но може да намали пълнотата при редки финансови събития, така че агентите за измами пропускат аномалии.

Mike Thrift

ai llm machine-learning

[Започни безплатно→](https://beancount.io/sign-up/?next=%2Fledger%2F) [Документация](https://beancount.io/bg/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
