aifinhub

Playground

Hallucination Detector for Financial Extractions

Paste source + LLM extraction. Every numeric claim is cross-checked against the source; ungrounded claims are flagged. Runs in your browser. Free.

Inputs
Source document + LLM extraction
Runtime
Instant
Privacy
Client-side · no upload
API key
Not required
Methodology
Open →

Claims detected

7

Grounded

2

Not grounded

5

Grounding score

29%

1 · Source document

2 · LLM extraction / output

3 · Markup

Company: SYNTHETIC_A Corp. Period: fiscal year ended 2025-12-31. Revenue: $2,847 million (18.1% YoY growth). Net income: $412 million. Operating cash flow: $780 million. R&D intensity: 12.3% of revenue. Notable: primary customer concentration exceeds 35% of revenue.

greengroundedrosenot grounded — likely hallucination

Ungrounded claims

  • currency$2,847 million
  • percent18.1%
  • currency$412 millionnearest in source: 2025
  • currency$780 millionnearest in source: 2025
  • percent35%

How grounding is checked

  • · Numbers in the output are extracted (currencies, plain numbers ≥ 1000, percents, dates).
  • · Each number is checked for direct substring presence in the source, then for within-1% numeric proximity.
  • · Dates get a looser year-level fallback.
  • · Prose-level fabrication is not detected. This pass catches the numeric class only — by far the most costly class in financial extractions.

See methodology for the full algorithm, limitations, and planned embedding-based prose checker.

Complementary tools

Planning estimates only — not financial, tax, or investment advice.