使用LLMs回答封闭域问题

背景

以下提示测试LLM回答封闭域问题的能力，这涉及回答属于特定主题或领域的问题。

注意

注意，由于任务的挑战性，当LLM对问题没有相关知识时，可能会产生幻觉。

提示

患者情况：
- 20岁女性
- 有厌食症和抑郁症史
- 血压100/50，脉搏50，身高5'5''
- 由营养师推荐，但她否认自己有病
- 报告饮食正常，但体重严重偏低

请将上述数据重新写成医疗记录，仅使用上述信息。

代码 / API

GPT-4 (OpenAI)

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
model="gpt-4",
messages=[
    {
    "role": "user",
    "content": "Patient’s facts:\n- 20 year old female\n- with a history of anerxia nervosa and depression\n- blood pressure 100/50, pulse 50, height 5’5’’\n- referred by her nutrionist but is in denial of her illness\n- reports eating fine but is severely underweight\n\nPlease rewrite the data above into a medical note, using exclusively the information above."
    }
],
temperature=1,
max_tokens=500,
top_p=1,
frequency_penalty=0,
presence_penalty=0
)

Mixtral MoE 8x7B Instruct (Fireworks)

import fireworks.client
fireworks.client.api_key = "<FIREWORKS_API_KEY>"
completion = fireworks.client.ChatCompletion.create(
    model="accounts/fireworks/models/mixtral-8x7b-instruct",
    messages=[
        {
        "role": "user",
        "content": "Patient’s facts:\n- 20 year old female\n- with a history of anerxia nervosa and depression\n- blood pressure 100/50, pulse 50, height 5’5’’\n- referred by her nutrionist but is in denial of her illness\n- reports eating fine but is severely underweight\n\nPlease rewrite the data above into a medical note, using exclusively the information above.",
        }
    ],
    stop=["<|im_start|>","<|im_end|>","<|endoftext|>"],
    stream=True,
    n=1,
    top_p=1,
    top_k=40,
    presence_penalty=0,
    frequency_penalty=0,
    prompt_truncate_len=1024,
    context_length_exceeded_behavior="truncate",
    temperature=0.9,
    max_tokens=4000
)

参考

• 人工通用智能的火花：GPT-4的早期实验 (2023年4月13日)