Detect hallucinations using specialised Ollama model bespoke-minicheck

Fact-Checking Workflow Documentation

Overview This workflow is designed for automated fact-checking of texts. It uses AI models to compare a given text with a list of facts and identify potential discrepancies or hallucinations.

Components

1. Input - The workflow can be initiated in two ways: a) Manually via the "When clicking 'Test workflow'" trigger b) By calling from another workflow via the "When Executed by Another Workflow" trigger - Required inputs: - facts: A list of verified facts - text: The text to be checked

2. Text Preparation - The "Code" node splits the input text into individual sentences - Takes into account date specifications and list elements

3. Fact Checking - Each sentence is individually compared with the given facts - Uses the "bespoke-minicheck" Ollama model for verification - The model responds with "Yes" or "No" for each sentence

4. Filtering and Aggregation - Sentences marked as "No" (not fact-based) are filtered - The filtered results are aggregated

5. Summary - A larger language model (Qwen2.5) creates a summary of the results - The summary contains: - Number of incorrect factual statements - List of incorrect statements - Final assessment of the article's accuracy