Detect Hallucination
Identifies fabricated facts or details a model added that aren't present in the input or provided context.
Detect Hallucination checks whether a response contains facts the model made up, information that isn’t backed by the input or context it was given. Run it as a direct hallucination check on generated content.
What it does
Detect Hallucination is an LLM-as-Judge eval. It reads the context and the generated output (and optionally the input), then returns a pass/fail on whether fabricated content is present.
Input
| Required Input | Type | Description |
|---|---|---|
output | string | Output generated by the model |
context | string | The context provided to the model |
| Optional Input | Type | Description |
|---|---|---|
input | string | Input provided to the model |
Output
| Field | Type | Description |
|---|---|---|
| Result | Pass / Fail | Passed means no hallucination is detected, Failed means hallucination is detected |
| Reason | string | A plain-language explanation of the evaluation |
Run it from code
Call evaluate() with the template name and the eval’s required inputs. It returns the score and the reason.
Note
Before running: install the SDK and set FI_API_KEY / FI_SECRET_KEY. The model argument in the snippets is the evaluator model Future AGI uses to run the eval; turing_flash is a fast default.
from fi.evals import evaluate
result = evaluate(
"detect_hallucination",
context="Honey never spoils because it has low moisture content and high acidity, creating an environment that resists bacteria and microorganisms. Archaeologists have even found pots of honey in ancient Egyptian tombs that are still perfectly edible.",
output="Honey doesn't spoil because its low moisture and high acidity prevent the growth of bacteria and other microbes.",
model="turing_flash",
)
print(result.score)
print(result.reason)import { evaluate } from "@future-agi/ai-evaluation";
const result = await evaluate(
"detect_hallucination",
{
context: "Honey never spoils because it has low moisture content and high acidity, creating an environment that resists bacteria and microorganisms. Archaeologists have even found pots of honey in ancient Egyptian tombs that are still perfectly edible.",
output: "Honey doesn't spoil because its low moisture and high acidity prevent the growth of bacteria and other microbes."
},
{ modelName: "turing_flash" }
);
console.log(result);When to use
Run Detect Hallucination wherever fabricated facts would be costly, and you want a direct signal on made-up content rather than a broader adherence score.
- Text, audio, image, and chat outputs generated from a fixed input or context
- RAG and retrieval pipelines, to catch fabricated details that slipped past retrieval-grounded generation
- Hallucination checks, as a targeted complement to Context Adherence and Groundedness
What to do when Detect Hallucination fails
If the content is evaluated as containing hallucinations (Failed) and you want to improve it:
- Ensure all claims in your output are explicitly supported by the source material
- Avoid extrapolating or generalizing beyond what is stated in the input
- Remove any specific details that aren’t mentioned in the source text
- Use qualifying language (like “may,” “could,” or “suggests”) when necessary
- Stick to paraphrasing rather than adding new information
- Double-check numerical values, dates, and proper nouns against the source
- Consider directly quoting from the source for critical information
Questions & Discussion