메뉴
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/vuralserhat86/antigravity-agentic-skills --skill llm-evaluation명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | llm_evaluation |
| router_kit | AIKit |
| description | Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks. |
| metadata | {"skillport":{"category":"auto-healed","tags":["accuracy","agents","algorithms","artificial intelligence","automation","benchmarking","chatbots","cognitive services","deep learning","embeddings","frameworks","generative ai","hallucination check","inference","large language models","llm","llm evaluation","machine learning","metrics","model fine-tuning","natural language processing","neural networks","nlp","openai","prompt engineering","rag","retrieval augmented generation","testing","tools","vector databases","workflow automation"]}} |
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
Fast, repeatable, scalable evaluation using computed scores.
Classification:
Retrieval (RAG):
Manual assessment for quality aspects difficult to automate.
Dimensions:
Use stronger LLMs to evaluate weaker model outputs.
Approaches:
from llm_eval import EvaluationSuite, Metric
# Define evaluation suite
suite = EvaluationSuite([
Metric.accuracy(),
Metric.bleu(),
Metric.bertscore(),
Metric.custom(name="groundedness", fn=check_groundedness)
])
# Prepare test cases
test_cases = [
{
"input": "What is the capital of France?",
"expected": "Paris",
"context": "France is a country in Europe. Paris is its capital."
},
# ... more test cases
]
# Run evaluation
results = suite.evaluate(
model=your_model,
test_cases=test_cases
)
print(f"Overall Accuracy: {results.metrics['accuracy']}")
print(f"BLEU Score: {results.metrics['bleu']}")
from nltk.translate.bleu_score import sentence_bleu, SmoothingFunction
def calculate_bleu(reference, hypothesis):
"""Calculate BLEU score between reference and hypothesis."""
smoothie = SmoothingFunction().method4
return sentence_bleu(
[reference.split()],
hypothesis.split(),
smoothing_function=smoothie
)
# Usage
bleu = calculate_bleu(
reference="The cat sat on the mat",
hypothesis="A cat is sitting on the mat"
)
from rouge_score import rouge_scorer
def calculate_rouge(reference, hypothesis):
"""Calculate ROUGE scores."""
scorer = rouge_scorer.RougeScorer(['rouge1', 'rouge2', 'rougeL'], use_stemmer=True)
scores = scorer.score(reference, hypothesis)
return {
'rouge1': scores['rouge1'].fmeasure,
'rouge2': scores['rouge2'].fmeasure,
'rougeL': scores['rougeL'].fmeasure
}
from bert_score import score
def calculate_bertscore(references, hypotheses):
"""Calculate BERTScore using pre-trained BERT."""
P, R, F1 = score(
hypotheses,
references,
lang='en',
model_type='microsoft/deberta-xlarge-mnli'
)
return {
'precision': P.mean().item(),
'recall': R.mean().item(),
'f1': F1.mean().item()
}
def calculate_groundedness(response, context):
"""Check if response is grounded in provided context."""
# Use NLI model to check entailment
from transformers import pipeline
nli = pipeline("text-classification", model="microsoft/deberta-large-mnli")
result = nli(f"{context} [SEP] {response}")[0]
# Return confidence that response is entailed by context
return result['score'] if result['label'] == 'ENTAILMENT' else 0.0
def calculate_toxicity(text):
"""Measure toxicity in generated text."""
from detoxify import Detoxify
results = Detoxify('original').predict(text)
return max(results.values()) # Return highest toxicity score
def calculate_factuality(claim, knowledge_base):
"""Verify factual claims against knowledge base."""
# Implementation depends on your knowledge base
# Could use retrieval + NLI, or fact-checking API
pass
def llm_judge_quality(response, question):
"""Use GPT-5 to judge response quality."""
prompt = f"""Rate the following response on a scale of 1-10 for:
1. Accuracy (factually correct)
2. Helpfulness (answers the question)
3. Clarity (well-written and understandable)
Question: {question}
Response: {response}
Provide ratings in JSON format:
{{
"accuracy": <1-10>,
"helpfulness": <1-10>,
"clarity": <1-10>,
"reasoning": "<brief explanation>"
}}
"""
result = openai.ChatCompletion.create(
model="gpt-5",
messages=[{"role": "user", "content": prompt}],
temperature=0
)
return json.loads(result.choices[0].message.content)
def compare_responses(question, response_a, response_b):
"""Compare two responses using LLM judge."""
prompt = f"""Compare these two responses to the question and determine which is better.
Question: {question}
Response A: {response_a}
Response B: {response_b}
Which response is better and why? Consider accuracy, helpfulness, and clarity.
Answer with JSON:
{{
"winner": "A" or "B" or "tie",
"reasoning": "<explanation>",
"confidence": <1-10>
}}
"""
result = openai.ChatCompletion.create(
model="gpt-5",
messages=[{"role": "user", "content": prompt}],
temperature=0
)
return json.loads(result.choices[0].message.content)
class AnnotationTask:
"""Structure for human annotation task."""
def __init__(self, response, question, context=None):
self.response = response
self.question = question
self.context = context
def get_annotation_form(self):
return {
"question": self.question,
"context": self.context,
"response": self.response,
"ratings": {
"accuracy": {
"scale": "1-5",
"description": "Is the response factually correct?"
},
"relevance": {
"scale": "1-5",
"description": "Does it answer the question?"
},
"coherence": {
"scale": "1-5",
"description": "Is it logically consistent?"
}
},
"issues": {
"factual_error": False,
"hallucination": False,
"off_topic": False,
"unsafe_content": False
},
"feedback": ""
}
from sklearn.metrics import cohen_kappa_score
def calculate_agreement(rater1_scores, rater2_scores):
"""Calculate inter-rater agreement."""
kappa = cohen_kappa_score(rater1_scores, rater2_scores)
interpretation = {
kappa < 0: "Poor",
kappa < 0.2: "Slight",
kappa < 0.4: "Fair",
kappa < 0.6: "Moderate",
kappa < 0.8: "Substantial",
kappa <= 1.0: "Almost Perfect"
}
return {
"kappa": kappa,
"interpretation": interpretation[True]
}
from scipy import stats
import numpy as np
class ABTest:
def __init__(self, variant_a_name="A", variant_b_name="B"):
self.variant_a = {"name": variant_a_name, "scores": []}
self.variant_b = {"name": variant_b_name, "scores": []}
def add_result(self, variant, score):
"""Add evaluation result for a variant."""
if variant == "A":
self.variant_a["scores"].append(score)
else:
self.variant_b["scores"].append(score)
def analyze(self, alpha=0.05):
"""Perform statistical analysis."""
a_scores = self.variant_a["scores"]
b_scores = self.variant_b["scores"]
# T-test
t_stat, p_value = stats.ttest_ind(a_scores, b_scores)
# Effect size (Cohen's d)
pooled_std = np.sqrt((np.std(a_scores)**2 + np.std(b_scores)**2) / 2)
cohens_d = (np.mean(b_scores) - np.mean(a_scores)) / pooled_std
return {
"variant_a_mean": np.mean(a_scores),
"variant_b_mean": np.mean(b_scores),
"difference": np.mean(b_scores) - np.mean(a_scores),
"relative_improvement": (np.mean(b_scores) - np.mean(a_scores)) / np.mean(a_scores),
"p_value": p_value,
"statistically_significant": p_value < alpha,
"cohens_d": cohens_d,
"effect_size": self.interpret_cohens_d(cohens_d),
"winner": "B" if np.mean(b_scores) > np.mean(a_scores) else "A"
}
@staticmethod
def interpret_cohens_d(d):
"""Interpret Cohen's d effect size."""
abs_d = abs(d)
if abs_d < 0.2:
return "negligible"
elif abs_d < 0.5:
return "small"
elif abs_d < 0.8:
return "medium"
else:
return "large"
class RegressionDetector:
def __init__(self, baseline_results, threshold=0.05):
self.baseline = baseline_results
self.threshold = threshold
def check_for_regression(self, new_results):
"""Detect if new results show regression."""
regressions = []
for metric in self.baseline.keys():
baseline_score = self.baseline[metric]
new_score = new_results.get(metric)
if new_score is None:
continue
# Calculate relative change
relative_change = (new_score - baseline_score) / baseline_score
# Flag if significant decrease
if relative_change < -self.threshold:
regressions.append({
"metric": metric,
"baseline": baseline_score,
"current": new_score,
"change": relative_change
})
return {
"has_regression": len(regressions) > 0,
"regressions": regressions
}
class BenchmarkRunner:
def __init__(self, benchmark_dataset):
self.dataset = benchmark_dataset
def run_benchmark(self, model, metrics):
"""Run model on benchmark and calculate metrics."""
results = {metric.name: [] for metric in metrics}
for example in self.dataset:
# Generate prediction
prediction = model.predict(example["input"])
# Calculate each metric
for metric in metrics:
score = metric.calculate(
prediction=prediction,
reference=example["reference"],
context=example.get("context")
)
results[metric.name].append(score)
# Aggregate results
return {
metric: {
"mean": np.mean(scores),
"std": np.std(scores),
"min": min(scores),
"max": max(scores)
}
for metric, scores in results.items()
}
Kaynak: Ragas Metrics & HuggingFace Evaluation Guide
| Aşama | Doğrulama |
|---|---|
| 1 | Test seti gerçek kullanıcı verilerini temsil ediyor mu? |
| 2 | Otomatik metrikler ile insan kararları uyuşuyor mu (Korrelasyon)? |
| 3 | Model güvenliği (PII sızıntısı, toksisite) garanti altında mı? |