Test fixture
Grounded answers under adversarial or missing-context prompts.
The model receives the prompt (and optional system message). The run uses scorer exact_match with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.
Answer only based on the document. If not present, reply exactly: Not stated Document: - Tool A supports CSV export. - Tool A has role-based access. - Tool A launched in 2022. Question: Which API version does Tool A use?
{
"expected": "Not stated"
}temperature
0
max_tokens
20
timeout (s)
120
type
scored
file
hallucination_easy_01.json