178 lines
7.3 KiB
Python
178 lines
7.3 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""幻觉/事实性校验（hallucination）单元测试：引用溯源 / 信度阈值 / 评测。"""
|
||
import os
|
||
import sys
|
||
import unittest
|
||
|
||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||
import _bootstrap # noqa: F401
|
||
|
||
from llm_gateway.hallucination import HallucinationGuard # noqa: E402
|
||
|
||
|
||
class CitationCheckTest(unittest.TestCase):
|
||
def setUp(self):
|
||
self.guard = HallucinationGuard(default_threshold=0.8)
|
||
|
||
def test_declared_sources_are_verified(self):
|
||
verdict = self.guard.check(
|
||
answer="炉温偏高应降温。[来源: 沸腾氯化炉异常处置SOP]",
|
||
sources=["沸腾氯化炉异常处置SOP", "交接班规范"],
|
||
)
|
||
self.assertTrue(verdict.supported)
|
||
self.assertEqual(verdict.action, "pass")
|
||
|
||
def test_missing_source_is_unsupported(self):
|
||
verdict = self.guard.check(
|
||
answer="应停机。[来源: 不存在的文档]",
|
||
sources=["沸腾氯化炉异常处置SOP"],
|
||
)
|
||
self.assertFalse(verdict.supported)
|
||
self.assertEqual(verdict.action, "unsupported")
|
||
self.assertIn("不存在的文档", verdict.missing_sources)
|
||
|
||
def test_no_citation_is_supported(self):
|
||
# 无引用声明 = 不判幻觉（引用为强制项由 RAG 模板保证）
|
||
verdict = self.guard.check(answer="按操作规程执行。", sources=[])
|
||
self.assertTrue(verdict.supported)
|
||
self.assertEqual(verdict.action, "pass")
|
||
|
||
|
||
class ConfidenceThresholdTest(unittest.TestCase):
|
||
def setUp(self):
|
||
self.guard = HallucinationGuard(default_threshold=0.8)
|
||
|
||
def test_low_confidence_high_stakes_human_review(self):
|
||
verdict = self.guard.check(
|
||
answer="建议立即停机。[来源: SOP]",
|
||
sources=["SOP"], confidence=0.55, high_stakes=True,
|
||
)
|
||
self.assertEqual(verdict.action, "human_review")
|
||
|
||
def test_high_confidence_high_stakes_passes(self):
|
||
verdict = self.guard.check(
|
||
answer="建议观察并记录。[来源: SOP]",
|
||
sources=["SOP"], confidence=0.95, high_stakes=True,
|
||
)
|
||
self.assertEqual(verdict.action, "pass")
|
||
|
||
def test_low_confidence_non_stakes_passes(self):
|
||
# 非高利害场景不启用阈值
|
||
verdict = self.guard.check(
|
||
answer="一般说明。[来源: 手册]", sources=["手册"],
|
||
confidence=0.3, high_stakes=False,
|
||
)
|
||
self.assertEqual(verdict.action, "pass")
|
||
|
||
def test_custom_threshold(self):
|
||
verdict = self.guard.check(
|
||
answer="处置建议。[来源: 手册]", sources=["手册"],
|
||
confidence=0.7, high_stakes=True, threshold=0.6,
|
||
)
|
||
self.assertEqual(verdict.action, "pass")
|
||
|
||
|
||
class EvaluateTest(unittest.TestCase):
|
||
def setUp(self):
|
||
self.guard = HallucinationGuard()
|
||
|
||
def test_evaluate_rates(self):
|
||
samples = [
|
||
{"answer": "a[来源: X]", "sources": ["X"], "confidence": 0.9, "high_stakes": True},
|
||
{"answer": "b[来源: Y]", "sources": ["Z"], "confidence": 0.9},
|
||
{"answer": "c[来源: X]", "sources": ["X"], "confidence": 0.4, "high_stakes": True},
|
||
]
|
||
report = self.guard.evaluate(samples)
|
||
self.assertEqual(report["total"], 3)
|
||
# 支持 2 条（a/c），human_review 1 条（c）
|
||
self.assertEqual(report["supported_rate"], round(2 / 3, 4))
|
||
self.assertEqual(report["human_review_rate"], round(1 / 3, 4))
|
||
self.assertEqual(len(report["samples"]), 3)
|
||
self.assertEqual(report["prompts"], {})
|
||
|
||
def test_empty_samples(self):
|
||
report = self.guard.evaluate([])
|
||
self.assertEqual(report["total"], 0)
|
||
self.assertEqual(report["samples"], [])
|
||
|
||
def test_audit_records(self):
|
||
self.guard.check("x[来源: A]", sources=["A"])
|
||
records = self.guard.drain_audit()
|
||
self.assertEqual(len(records), 1)
|
||
self.assertEqual(records[0]["action"], "pass")
|
||
|
||
|
||
class PromptLinkageTest(unittest.TestCase):
|
||
"""Issue #47：与 Prompt 版本库的联动（check / evaluate 按 name@version 分解）。"""
|
||
|
||
def setUp(self):
|
||
from llm_gateway.prompts import PromptRegistry
|
||
|
||
self.guard = HallucinationGuard()
|
||
self.reg = PromptRegistry()
|
||
self.reg.update("qa", "问题：{query}", "1.0.0")
|
||
self.reg.update("qa", "问题：{query} 请引用SOP", "1.0.1")
|
||
self.reg.promote("qa", "1.0.1")
|
||
|
||
def test_check_records_prompt_version(self):
|
||
verdict = self.guard.check(
|
||
"按SOP处理。[来源: SOP]", sources=["SOP"],
|
||
prompt_name="qa", prompt_version="1.0.0",
|
||
)
|
||
self.assertEqual(verdict.prompt_name, "qa")
|
||
self.assertEqual(verdict.prompt_version, "1.0.0")
|
||
records = self.guard.drain_audit()
|
||
self.assertEqual(records[0]["prompt_name"], "qa")
|
||
self.assertEqual(records[0]["prompt_version"], "1.0.0")
|
||
|
||
def test_evaluate_breakdown_by_prompt_version(self):
|
||
samples = [
|
||
{"answer": "好[来源: X]", "sources": ["X"], "prompt_name": "qa", "prompt_version": "1.0.0"},
|
||
{"answer": "坏[来源: Y]", "sources": ["Z"], "prompt_name": "qa", "prompt_version": "1.0.0"},
|
||
{"answer": "好[来源: X]", "sources": ["X"], "prompt_name": "qa"}, # 缺省取当前默认 1.0.1
|
||
]
|
||
report = self.guard.evaluate(samples, registry=self.reg)
|
||
prompts = report["prompts"]
|
||
self.assertIn("qa@1.0.0", prompts)
|
||
self.assertIn("qa@1.0.1", prompts)
|
||
self.assertEqual(prompts["qa@1.0.0"]["total"], 2)
|
||
self.assertEqual(prompts["qa@1.0.0"]["supported"], 1)
|
||
self.assertEqual(prompts["qa@1.0.1"]["total"], 1)
|
||
# 逐样本记录携带 prompt 标签
|
||
self.assertEqual(report["samples"][0]["prompt"], "qa@1.0.0")
|
||
|
||
def test_evaluate_explicit_version_validated(self):
|
||
samples = [
|
||
{"answer": "x[来源: A]", "sources": ["A"], "prompt_name": "qa", "prompt_version": "1.0.1"},
|
||
]
|
||
report = self.guard.evaluate(samples, registry=self.reg)
|
||
self.assertIn("qa@1.0.1", report["prompts"])
|
||
self.assertNotIn("prompt_error", report["samples"][0])
|
||
|
||
def test_evaluate_unknown_prompt_does_not_crash(self):
|
||
samples = [
|
||
{"answer": "x[来源: A]", "sources": ["A"], "prompt_name": "not_exist"},
|
||
]
|
||
report = self.guard.evaluate(samples, registry=self.reg)
|
||
self.assertEqual(report["total"], 1)
|
||
self.assertEqual(report["samples"][0]["prompt"], "not_exist@unknown")
|
||
self.assertIn("prompt_error", report["samples"][0])
|
||
|
||
def test_render_report_contains_rates_and_prompt_section(self):
|
||
samples = [
|
||
{"answer": "好[来源: X]", "sources": ["X"], "prompt_name": "qa", "prompt_version": "1.0.0"},
|
||
{"answer": "坏[来源: 不存在]", "sources": ["Z"], "prompt_name": "qa", "prompt_version": "1.0.0"},
|
||
]
|
||
report = self.guard.evaluate(samples, registry=self.reg)
|
||
text = self.guard.render_evaluation_report(report)
|
||
self.assertIn("样本总数：2", text)
|
||
self.assertIn("支持率", text)
|
||
self.assertIn("## 按 Prompt 版本分解", text)
|
||
self.assertIn("qa@1.0.0", text)
|
||
self.assertIn("## 未通过样本明细", text)
|
||
self.assertIn("不存在", text)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|