Mahdi Bazrafshan
e1ca9f4127
Why: - Manager deliverable for human evaluation across 10 benchmark documents. Changes: - Report markdown, scored CSV, chart generator, and SVG assets - Linked from docs/README.md Co-authored-by: Cursor <cursoragent@cursor.com>
17 lines
1.3 KiB
XML
17 lines
1.3 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<svg xmlns="http://www.w3.org/2000/svg" width="520" height="280" viewBox="0 0 520 280" role="img" aria-label="Agreement breakdown">
|
|
<title>Agreement breakdown</title>
|
|
<rect width="520" height="280" fill="#ffffff"/>
|
|
<text x="20" y="28" font-family="Inter, system-ui, sans-serif" font-size="16" font-weight="700" fill="#111827">Human vs LLM-as-Judge agreement</text>
|
|
<text x="20" y="48" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#6b7280">Tier match on answer quality (n=60)</text>
|
|
<path d="M 160 140 L 160 50 A 90 90 0 1 1 123.39 222.22 Z" fill="#047857"/>
|
|
<path d="M 160 140 L 160 50 A 90 90 0 0 1 150.59 50.49 Z" fill="#d97706"/>
|
|
<path d="M 160 140 L 160 50 A 90 90 0 0 1 160.00 50.00 Z" fill="#be123c"/>
|
|
<rect x="300" y="80" width="14" height="14" rx="2" fill="#047857"/>
|
|
<text x="322" y="92" font-family="Inter, system-ui, sans-serif" font-size="13" fill="#111827">Agree: 34 (57%)</text>
|
|
<rect x="300" y="116" width="14" height="14" rx="2" fill="#d97706"/>
|
|
<text x="322" y="128" font-family="Inter, system-ui, sans-serif" font-size="13" fill="#111827">Partial: 25 (42%)</text>
|
|
<rect x="300" y="152" width="14" height="14" rx="2" fill="#be123c"/>
|
|
<text x="322" y="164" font-family="Inter, system-ui, sans-serif" font-size="13" fill="#111827">Disagree: 1 (2%)</text>
|
|
</svg>
|