llm-evaluation-dashboard / data /sample_evaluations.json
emhaihsan's picture
Initial commit: LLM Evaluation Dashboard
99f6668
Raw
History Blame Contribute Delete
1.3 kB
{
"examples": [
{
"name": "Exact Match",
"ground_truth": "The cat sat on the mat",
"prediction": "The cat sat on the mat",
"description": "Perfect match - all metrics should be 1.0"
},
{
"name": "Paraphrase",
"ground_truth": "The cat sat on the mat",
"prediction": "The cat was sitting on the mat",
"description": "Same meaning, different words - BERT > BLEU"
},
{
"name": "Partial Match",
"ground_truth": "The cat sat on the mat and looked outside",
"prediction": "The cat sat on the mat",
"description": "Incomplete - brevity penalty applies"
},
{
"name": "Wrong Answer",
"ground_truth": "Paris is the capital of France",
"prediction": "Berlin is the capital of France",
"description": "Completely wrong but similar structure"
},
{
"name": "Extra Content",
"ground_truth": "The cat sat on the mat",
"prediction": "The cat sat on the mat and then jumped off quickly",
"description": "Extra words added - recall suffers"
},
{
"name": "Word Reorder",
"ground_truth": "The cat sat on the mat",
"prediction": "On the mat sat the cat",
"description": "Same words, different order - ROGUE-L handles this"
}
]
}