expect_no_hallucination

Test that an LLM response does not contain hallucinated information
when compared against ground truth.

A production-grade AI toolkit for R featuring a layered
architecture (Specification, Utilities, Providers, Core), request
interception support, robust error handling with exponential retry
delays, support for multiple AI model providers ('OpenAI',
'Anthropic', etc.), local small language model inference,
distributed 'MCP' ecosystem, multi-agent orchestration, progressive
knowledge loading through skills, and a global skill store for
sharing AI capabilities.

Yonghe Xia

aisdk

Unified Interface for AI Model Providers

expect_no_hallucination function

<dl><dt>response</dt>
<dd>The LLM response to check.</dd>
<dt>ground_truth</dt>
<dd>The factual information to check against.</dd>
<dt>model</dt>
<dd>Model to use for checking.</dd>
<dt>tolerance</dt>
<dd>Allowed deviation (0 = strict, 1 = lenient).</dd>
<dt>info</dt>
<dd>Additional information for failure message.</dd></dl>

Arguments

Expect No Hallucination — expect_no_hallucination

<dl>

<dt>response</dt>
<dd>The LLM response to check.</dd>


<dt>ground_truth</dt>
<dd>The factual information to check against.</dd>


<dt>model</dt>
<dd>Model to use for checking.</dd>


<dt>tolerance</dt>
<dd>Allowed deviation (0 = strict, 1 = lenient).</dd>


<dt>info</dt>
<dd>Additional information for failure message.</dd>

</dl>

expect_no_hallucination: Expect No Hallucination

Description

Usage

Arguments