语言任务的指标：困惑度与BLEU

Python 中的 LLM 入门

Jasmin Ludolf

Senior Data Science Content Developer, DataCamp

LLM任务与指标

语言任务的评估指标

困惑度（Perplexity）

衡量模型对下一个词预测的准确性与置信度
困惑度越低＝置信度越高

input_text = "Latest research findings in Antarctica show"

generated_text = "Latest research findings in Antarctica show that the ice sheet 
is melting faster than previously thought."


# Encode the prompt, generate text and decode it
input_text_ids = tokenizer.encode(input_text, return_tensors="pt")
output = model.generate(input_text_ids, max_length=20)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)

困惑度输出

perplexity = evaluate.load("perplexity", module_type="metric")
results = perplexity.compute(predictions=generated_text, model_id="gpt2")

print(results)

{'perplexities': [245.63299560546875, 520.3106079101562, ....], 
 'mean_perplexity': 2867.7229790460497}

print(results["mean_perplexity"])

2867.7229790460497

与基线结果对比

BLEU

基于人工参考评估翻译质量
预测：LLM输出
参考：人工参考

bleu = evaluate.load("bleu")


input_text = "Latest research findings in Antarctica show"
references = [["Latest research findings in Antarctica show significant ice loss due to 
               climate change.", "Latest research findings in Antarctica show that the ice 
               sheet is melting faster than previously thought."]]
generated_text = "Latest research findings in Antarctica show that the ice sheet is melting 
               faster than previously thought."

BLEU输出

results = bleu.compute(predictions=[generated_text], references=references)
print(results)

{'bleu': 1.0, 
 'precisions': [1.0, 1.0, 1.0, 1.0], 
 'brevity_penalty': 1.0, 
 'length_ratio': 1.2142857142857142, 
 'translation_length': 17, 
 'reference_length': 14}

0–1分：越接近1＝相似度越高

让我们练习！

Python 中的 LLM 入门