docs(eval): add human evaluation report for fixed_size ±3
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>
This commit is contained in:
40
docs/assets/human-eval/human-vs-llm-by-document.svg
Normal file
40
docs/assets/human-eval/human-vs-llm-by-document.svg
Normal file
@@ -0,0 +1,40 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="900" height="420" viewBox="0 0 900 420" role="img" aria-label="Human vs LLM by document">
|
||||
<title>Human vs LLM by document</title>
|
||||
<rect width="900" height="420" fill="#ffffff"/>
|
||||
<text x="20" y="28" font-family="Inter, system-ui, sans-serif" font-size="16" font-weight="700" fill="#111827">Human score vs LLM answer similarity by document</text>
|
||||
<rect x="620" y="14" width="12" height="12" rx="2" fill="#14b8a6"/>
|
||||
<text x="638" y="25" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">Human (1–5)</text>
|
||||
<rect x="760" y="14" width="12" height="12" rx="2" fill="#f59e0b"/>
|
||||
<text x="778" y="25" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">LLM similarity (1–10)</text>
|
||||
<rect x="59.9" y="99.7" width="26.5" height="232.3" rx="3" fill="#14b8a6"/>
|
||||
<rect x="92.4" y="104.2" width="26.5" height="227.8" rx="3" fill="#f59e0b"/>
|
||||
<text x="89.4" y="384" text-anchor="end" transform="rotate(-32 89.4 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">bazresi</text>
|
||||
<rect x="142.7" y="117.6" width="26.5" height="214.4" rx="3" fill="#14b8a6"/>
|
||||
<rect x="175.2" y="90.8" width="26.5" height="241.2" rx="3" fill="#f59e0b"/>
|
||||
<text x="172.2" y="384" text-anchor="end" transform="rotate(-32 172.2 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">customer1</text>
|
||||
<rect x="225.5" y="90.8" width="26.5" height="241.2" rx="3" fill="#14b8a6"/>
|
||||
<rect x="258.0" y="108.7" width="26.5" height="223.3" rx="3" fill="#f59e0b"/>
|
||||
<text x="255.0" y="384" text-anchor="end" transform="rotate(-32 255.0 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">fire</text>
|
||||
<rect x="308.3" y="126.5" width="26.5" height="205.5" rx="3" fill="#14b8a6"/>
|
||||
<rect x="340.8" y="104.2" width="26.5" height="227.8" rx="3" fill="#f59e0b"/>
|
||||
<text x="337.8" y="384" text-anchor="end" transform="rotate(-32 337.8 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">havades-ind</text>
|
||||
<rect x="391.1" y="117.6" width="26.5" height="214.4" rx="3" fill="#14b8a6"/>
|
||||
<rect x="423.6" y="95.3" width="26.5" height="236.7" rx="3" fill="#f59e0b"/>
|
||||
<text x="420.6" y="384" text-anchor="end" transform="rotate(-32 420.6 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">havades</text>
|
||||
<rect x="473.9" y="99.7" width="26.5" height="232.3" rx="3" fill="#14b8a6"/>
|
||||
<rect x="506.4" y="81.9" width="26.5" height="250.1" rx="3" fill="#f59e0b"/>
|
||||
<text x="503.4" y="384" text-anchor="end" transform="rotate(-32 503.4 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">lifetime-ind</text>
|
||||
<rect x="556.7" y="72.9" width="26.5" height="259.1" rx="3" fill="#14b8a6"/>
|
||||
<rect x="589.2" y="77.4" width="26.5" height="254.6" rx="3" fill="#f59e0b"/>
|
||||
<text x="586.2" y="384" text-anchor="end" transform="rotate(-32 586.2 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">moavenin</text>
|
||||
<rect x="639.5" y="81.9" width="26.5" height="250.1" rx="3" fill="#14b8a6"/>
|
||||
<rect x="672.0" y="81.9" width="26.5" height="250.1" rx="3" fill="#f59e0b"/>
|
||||
<text x="669.0" y="384" text-anchor="end" transform="rotate(-32 669.0 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">Refah</text>
|
||||
<rect x="722.3" y="108.7" width="26.5" height="223.3" rx="3" fill="#14b8a6"/>
|
||||
<rect x="754.8" y="90.8" width="26.5" height="241.2" rx="3" fill="#f59e0b"/>
|
||||
<text x="751.8" y="384" text-anchor="end" transform="rotate(-32 751.8 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">website</text>
|
||||
<rect x="805.1" y="99.7" width="26.5" height="232.3" rx="3" fill="#14b8a6"/>
|
||||
<rect x="837.6" y="104.2" width="26.5" height="227.8" rx="3" fill="#f59e0b"/>
|
||||
<text x="834.6" y="384" text-anchor="end" transform="rotate(-32 834.6 384)" font-family="Inter, system-ui, sans-serif" font-size="11" fill="#111827">lifetime-comp</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 3.9 KiB |
Reference in New Issue
Block a user