logprobs 参数时，API 会返回每个输出标记的对数概率，以及每个标记位置上最可能的几个标记及其对数概率的有限数量。https://cookbook.openai.com/examples/using_logprobs
相关的请求参数包括：
logprobs：是否返回输出标记的对数概率。如果设置为 true，则返回消息内容中每个输出标记的对数概率。目前在gpt-4-vision-preview模型中不可用。top_logprobs：一个介于 0 和 5 之间的整数，指定要在每个标记位置返回的最可能标记的数量，每个标记都有一个关联的对数概率。如果使用了此参数，logprobs必须设置为 true。
输出标记的对数概率表示在给定上下文的情况下，每个标记出现在序列中的可能性。简单来说，对数概率是 log(p)，其中 p 是基于上下文中先前标记的概率。关于 logprobs 的一些关键点：
- 较高的对数概率表明在该上下文中标记出现的可能性较高。这使用户能够评估模型对其输出的信心程度，或者探索模型考虑的替代响应。
- 对数概率可以是任何负数或
0.0。0.0对应于 100% 的概率。 - 对数概率允许我们计算序列的联合概率，即个别标记的对数概率之和。这对于评分和排名模型输出很有用。另一种常见的方法是取一个句子的每个标记的平均对数概率来选择最佳生成结果。
- 我们可以检查分配给不同候选标记的
logprobs，以了解模型考虑的哪些选项是合理的或不合理的。
logprobs使用案例
分类任务
大型语言模型在许多分类任务上表现出色，但准确地衡量模型对其输出的信心可能具有挑战性。logprobs 提供了与每个类别预测相关联的概率，使用户能够设置自己的分类或置信度阈值。
CLASSIFICATION_PROMPT = """You will be given a headline of a news article.
Classify the article into one of the following categories: Technology, Politics, Sports, and Art.
Return only the name of the category, and nothing else.
MAKE SURE your output is one of the four categories stated.
Article headline: {headline}"""
headlines = [
"Tech Giant Unveils Latest Smartphone Model with Advanced Photo-Editing Features.",
"Local Mayor Launches Initiative to Enhance Urban Public Transport.",
"Tennis Champion Showcases Hidden Talents in Symphony Orchestra Debut",
]
for headline in headlines:
print(f"nHeadline: {headline}")
API_RESPONSE = get_completion(
[{"role": "user", "content": CLASSIFICATION_PROMPT.format(headline=headline)}],
model="gpt-4",
logprobs=True,
top_logprobs=2,
)
top_two_logprobs = API_RESPONSE.choices[0].logprobs.content[0].top_logprobs
html_content = ""
for i, logprob in enumerate(top_two_logprobs, start=1):
html_content = (
f"<span style='color: cyan'>Output token {i}:</span> {logprob.token}, "
f"<span style='color: darkorange'>logprobs:</span> {logprob.logprob}, "
f"<span style='color: magenta'>linear probability:</span> {np.round(np.exp(logprob.logprob)*100,2)}%<br>"
)
display(HTML(html_content))
print("n")
检索（问答）评估
logprobs 可以帮助在检索应用中进行自我评估。在问答示例中，模型输出一个虚构的 has_sufficient_context_for_answer 布尔值，它可以作为答案是否包含在检索内容中的置信度分数。这种类型的评估可以减少基于检索的幻觉，并增强准确性。
# Article retrieved
ada_lovelace_article = """Augusta Ada King, Countess of Lovelace (née Byron; 10 December 1815 – 27 November 1852) was an English mathematician and writer, chiefly known for her work on Charles Babbage's proposed mechanical general-purpose computer, the Analytical Engine. She was the first to recognise that the machine had applications beyond pure calculation.
Ada Byron was the only legitimate child of poet Lord Byron and reformer Lady Byron. All Lovelace's half-siblings, Lord Byron's other children, were born out of wedlock to other women. Byron separated from his wife a month after Ada was born and left England forever. He died in Greece when Ada was eight. Her mother was anxious about her upbringing and promoted Ada's interest in mathematics and logic in an effort to prevent her from developing her father's perceived insanity. Despite this, Ada remained interested in him, naming her two sons Byron and Gordon. Upon her death, she was buried next to him at her request. Although often ill in her childhood, Ada pursued her studies assiduously. She married William King in 1835. King was made Earl of Lovelace in 1838, Ada thereby becoming Countess of Lovelace.
Her educational and social exploits brought her into contact with scientists such as Andrew Crosse, Charles Babbage, Sir David Brewster, Charles Wheatstone, Michael Faraday, and the author Charles Dickens, contacts which she used to further her education. Ada described her approach as "poetical science" and herself as an "Analyst (& Metaphysician)".
When she was eighteen, her mathematical talents led her to a long working relationship and friendship with fellow British mathematician Charles Babbage, who is known as "the father of computers". She was in particular interested in Babbage's work on the Analytical Engine. Lovelace first met him in June 1833, through their mutual friend, and her private tutor, Mary Somerville.
Between 1842 and 1843, Ada translated an article by the military engineer Luigi Menabrea (later Prime Minister of Italy) about the Analytical Engine, supplementing it with an elaborate set of seven notes, simply called "Notes".
Lovelace's notes are important in the early history of computers, especially since the seventh one contained what many consider to be the first computer program—that is, an algorithm designed to be carried out by a machine. Other historians reject this perspective and point out that Babbage's personal notes from the years 1836/1837 contain the first programs for the engine. She also developed a vision of the capability of computers to go beyond mere calculating or number-crunching, while many others, including Babbage himself, focused only on those capabilities. Her mindset of "poetical science" led her to ask questions about the Analytical Engine (as shown in her notes) examining how individuals and society relate to technology as a collaborative tool.
"""
# Questions that can be easily answered given the article
easy_questions = [
"What nationality was Ada Lovelace?",
"What was an important finding from Lovelace's seventh note?",
]
# Questions that are not fully covered in the article
medium_questions = [
"Did Lovelace collaborate with Charles Dickens",
"What concepts did Lovelace build with Charles Babbage",
]
PROMPT = """You retrieved this article: {article}. The question is: {question}.
Before even answering the question, consider whether you have sufficient information in the article to answer the question fully.
Your output should JUST be the boolean true or false, of if you have sufficient information in the article to answer the question.
Respond with just one word, the boolean true or false. You must output the word 'True', or the word 'False', nothing else.
"""
自动补全
logprobs 可以帮助我们决定在用户输入时如何建议单词。
sentence_list = [
"My",
"My least",
"My least favorite",
"My least favorite TV",
"My least favorite TV show",
"My least favorite TV show is",
"My least favorite TV show is Breaking Bad",
]
计算困惑度
logprobs 可以用于帮助我们评估模型对结果的整体信心，并帮助我们比较来自不同提示的结果的置信度。
prompts = [
"In a short sentence, has artifical intelligence grown in the last decade?",
"In a short sentence, what are your thoughts on the future of artificial intelligence?",
]
for prompt in prompts:
API_RESPONSE = get_completion(
[{"role": "user", "content": prompt}],
model="gpt-3.5-turbo",
logprobs=True,
)
logprobs = [token.logprob for token in API_RESPONSE.choices[0].logprobs.content]
response_text = API_RESPONSE.choices[0].message.content
response_text_tokens = [token.token for token in API_RESPONSE.choices[0].logprobs.content]
max_starter_length = max(len(s) for s in ["Prompt:", "Response:", "Tokens:", "Logprobs:", "Perplexity:"])
max_token_length = max(len(s) for s in response_text_tokens)
formatted_response_tokens = [s.rjust(max_token_length) for s in response_text_tokens]
formatted_lps = [f"{lp:.2f}".rjust(max_token_length) for lp in logprobs]
perplexity_score = np.exp(-np.mean(logprobs))
print("Prompt:".ljust(max_starter_length), prompt)
print("Response:".ljust(max_starter_length), response_text, "n")
print("Tokens:".ljust(max_starter_length), " ".join(formatted_response_tokens))
print("Logprobs:".ljust(max_starter_length), " ".join(formatted_lps))
print("Perplexity:".ljust(max_starter_length), perplexity_score, "n")
