Hallucination metric assigns only either 0.0 or 1.0 score

[jmaczan]

Describe the bug
Hallucination metric score is being set to either 0.0 or 1.0. It never sets a score to a value in between of 0.0 and 1.0

To Reproduce
Steps to reproduce the behavior:

1. Create test cases where actual_output overlaps with context
2. Use hallucination metric to measure it
3. Run evaluation
4. Check hallucination score

Expected behavior
The hallucination score value is a continuous spectrum of real values <0.0; 1.0>

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: [e.g. iOS] Windows 11
• Browser [e.g. chrome, safari] Chrome
• Version [e.g. 22] 122

Smartphone (please complete the following information):

• Device: [e.g. iPhone6]
• OS: [e.g. iOS8.1]
• Browser [e.g. stock browser, safari]
• Version [e.g. 22]

Additional context
This problem might be connected with another one (the same test can get 0.0 in one run and 1.0 in another run, despite having the same input values)

[penguine-ip]

Can you provide an example test case that has this behvaior?