Bewertung von KI‑Modellen: Leitfaden zu Metriken und Benchmarks

Eine umfassende Bewertung ist entscheidend für die korrekte Modellauswahl. In diesem Leitfaden betrachten wir die Metriken und Benchmarks, die bei der Evaluierung von KI‑Modellen verwendet werden.

Grundlegende Metriken

Perplexity

Misst, wie gut das Sprachmodell Text vorhersagt:

1import torch
2import math
3
4def calculate_perplexity(model, tokenizer, text):
5    encodings = tokenizer(text, return_tensors="pt")
6    
7    with torch.no_grad():
8        outputs = model(**encodings, labels=encodings["input_ids"])
9        loss = outputs.loss
10    
11    perplexity = math.exp(loss.item())
12    return perplexity
13
14# Low perplexity = Better model
15# Typical values: 5-20 (good), >100 (bad)

Accuracy

Korrekte Vorhersagerate:

1def accuracy(predictions, labels):
2    correct = sum(p == l for p, l in zip(predictions, labels))
3    return correct / len(labels)

F1-Score

Balance zwischen Precision und Recall:

1from sklearn.metrics import f1_score, precision_score, recall_score
2
3def calculate_metrics(predictions, labels):
4    return {
5        "precision": precision_score(labels, predictions, average="weighted"),
6        "recall": recall_score(labels, predictions, average="weighted"),
7        "f1": f1_score(labels, predictions, average="weighted")
8    }
9## LLM-Benchmarks
10
11### MMLU (Massive Multitask Language Understanding)
12
13Multiple-Choice-Fragen in 57 Fachgebieten:
14
15```python
16def evaluate_mmlu(model, dataset):
17    results = {}
18    
19    for subject in dataset.subjects:
20        correct = 0
21        total = 0
22        
23        for question in dataset.get_questions(subject):
24            prompt = format_mcq_prompt(question)
25            response = model.generate(prompt)
26            predicted = extract_answer(response)
27            
28            if predicted == question.correct_answer:
29                correct += 1
30            total += 1
31        
32        results[subject] = correct / total
33    
34    return {
35        "subjects": results,
36        "average": sum(results.values()) / len(results)
37    }

MMLU-Ergebnisse (2024):

HellaSwag

Alltagslogisches Schlussfolgern:

1Context: "A woman is outside with a bucket and a dog. 
2The dog is running around trying to avoid a bath. She..."
3
4Options:
5A) rinses the dog off with a hose (correct)
6B) calls the dog and feeds it
7C) throws the bucket at the dog
8D) walks into the house

TruthfulQA

Messung von Halluzinationen und Wahrhaftigkeit:

1def evaluate_truthfulness(model, questions):
2    truthful_count = 0
3    informative_count = 0
4    
5    for q in questions:
6        response = model.generate(q.question)
7        
8        # Human evaluation or classifier
9        is_truthful = check_truthfulness(response, q.ground_truth)
10        is_informative = check_informativeness(response)
11        
12        if is_truthful:
13            truthful_count += 1
14        if is_informative:
15            informative_count += 1
16    
17    return {
18        "truthful": truthful_count / len(questions),
19        "informative": informative_count / len(questions)
20    }

HumanEval

Fähigkeit zur Codegenerierung:

1def evaluate_humaneval(model, problems):
2    pass_at_1 = 0
3    pass_at_10 = 0
4    
5    for problem in problems:
6        solutions = [model.generate_code(problem.prompt) for _ in range(10)]
7        
8        passed = [run_tests(sol, problem.tests) for sol in solutions]
9        
10        if passed[0]:
11            pass_at_1 += 1
12        if any(passed):
13            pass_at_10 += 1
14    
15    return {
16        "pass@1": pass_at_1 / len(problems),
17        "pass@10": pass_at_10 / len(problems)
18    }

MT-Bench

Qualität mehrstufiger Konversationen:

1def mt_bench_evaluate(model, conversations):
2    scores = []
3    
4    for conv in conversations:
5        # Multi-turn dialog
6        responses = []
7        for turn in conv.turns:
8            response = model.generate(turn.prompt, history=responses)
9            responses.append(response)
10        
11        # GPT judge scoring (1-10)
12        score = gpt4_judge(conv.turns, responses)
13        scores.append(score)
14    
15    return sum(scores) / len(scores)
16## RAG-Bewertung
17
18### Retrieval-Metriken
19
20```python
21def retrieval_metrics(retrieved_docs, relevant_docs, k=10):
22    retrieved_k = retrieved_docs[:k]
23    relevant_set = set(relevant_docs)
24    
25    # Recall@K
26    retrieved_relevant = len(set(retrieved_k) & relevant_set)
27    recall_k = retrieved_relevant / len(relevant_set)
28    
29    # Precision@K
30    precision_k = retrieved_relevant / k
31    
32    # MRR (Mean Reciprocal Rank)
33    mrr = 0
34    for i, doc in enumerate(retrieved_k):
35        if doc in relevant_set:
36            mrr = 1 / (i + 1)
37            break
38    
39    return {
40        "recall@k": recall_k,
41        "precision@k": precision_k,
42        "mrr": mrr
43    }

RAGAS-Metriken

1from ragas import evaluate
2from ragas.metrics import faithfulness, answer_relevancy, context_precision
3
4def evaluate_rag(questions, answers, contexts, ground_truths):
5    dataset = {
6        "question": questions,
7        "answer": answers,
8        "contexts": contexts,
9        "ground_truth": ground_truths
10    }
11    
12    results = evaluate(
13        dataset,
14        metrics=[faithfulness, answer_relevancy, context_precision]
15    )
16    
17    return results

Textgenerierungsmetriken

BLEU-Score

1from nltk.translate.bleu_score import sentence_bleu
2
3def calculate_bleu(reference, candidate):
4    reference_tokens = [reference.split()]
5    candidate_tokens = candidate.split()
6    
7    return sentence_bleu(reference_tokens, candidate_tokens)

ROUGE-Score

1from rouge_score import rouge_scorer
2
3def calculate_rouge(reference, candidate):
4    scorer = rouge_scorer.RougeScorer(['rouge1', 'rouge2', 'rougeL'])
5    scores = scorer.score(reference, candidate)
6    
7    return {
8        "rouge1": scores['rouge1'].fmeasure,
9        "rouge2": scores['rouge2'].fmeasure,
10        "rougeL": scores['rougeL'].fmeasure
11    }

BERTScore

Semantische Ähnlichkeit:

1from bert_score import score
2
3def calculate_bertscore(references, candidates):
4    P, R, F1 = score(candidates, references, lang="tr")
5    return {
6        "precision": P.mean().item(),
7        "recall": R.mean().item(),
8        "f1": F1.mean().item()
9    }

LLM-as-Judge

Bewertung mit GPT:

1def llm_judge(response, criteria):
2    prompt = f"""Evaluate the following response.
3
4Response: {response}
5
6Evaluation criteria:
7{criteria}
8
9Rate from 1-10 and explain your reasoning.
10JSON format: {{"score": X, "reasoning": "..."}}
11"""
12    
13    result = client.chat.completions.create(
14        model="gpt-4-turbo",
15        response_format={"type": "json_object"},
16        messages=[{"role": "user", "content": prompt}]
17    )
18    
19    return json.loads(result.choices[0].message.content)

A/B-Test-Framework

1class ModelABTest:
2    def __init__(self, model_a, model_b):
3        self.model_a = model_a
4        self.model_b = model_b
5        self.results = {"a_wins": 0, "b_wins": 0, "ties": 0}
6    
7    def compare(self, prompt):
8        response_a = self.model_a.generate(prompt)
9        response_b = self.model_b.generate(prompt)
10        
11        # Blind comparison with LLM judge
12        winner = self.judge_comparison(prompt, response_a, response_b)
13        
14        self.results[f"{winner}_wins"] += 1
15        
16        return {
17            "response_a": response_a,
18            "response_b": response_b,
19            "winner": winner
20        }
21    
22    def get_statistics(self):
23        total = sum(self.results.values())
24        return {
25            "model_a_win_rate": self.results["a_wins"] / total,
26            "model_b_win_rate": self.results["b_wins"] / total,
27            "tie_rate": self.results["ties"] / total
28        }
29## Leaderboard-Vergleich
30
31### Open LLM Leaderboard
32

1
2## Enterprise-Bewertung
3
4### Benutzerdefiniertes Benchmark
5
6```python
7class EnterpriseEvaluation:
8    def __init__(self, model, test_cases):
9        self.model = model
10        self.test_cases = test_cases
11    
12    def evaluate(self):
13        results = {
14            "accuracy": [],
15            "latency": [],
16            "cost": [],
17            "safety": []
18        }
19        
20        for case in self.test_cases:
21            start = time.time()
22            response = self.model.generate(case.prompt)
23            latency = time.time() - start
24            
25            results["latency"].append(latency)
26            results["accuracy"].append(
27                self.check_accuracy(response, case.expected)
28            )
29            results["safety"].append(
30                self.check_safety(response)
31            )
32        
33        return {
34            "avg_accuracy": np.mean(results["accuracy"]),
35            "p95_latency": np.percentile(results["latency"], 95),
36            "safety_rate": np.mean(results["safety"])
37        }

Fazit

Die Modellevaluierung ist ein entscheidender Schritt für den Erfolg von KI-Projekten. Mit den richtigen Metriken und Benchmarks können Sie fundierte Modellentscheidungen treffen und eine kontinuierliche Verbesserung sicherstellen.

Bei Veni AI bieten wir Evaluierungsdienste für Unternehmensmodelle an.