|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/gpt-vs-gemini-for-structured-information-extraction/
课程评论：没有评论
课程名称：测量和提高大型语言模型（LLM）结构化输出的准确性 概述：自然语言处理（NLP）通常被视为自然语言理解（NLU）与自然语言生成（NLG）两个领域的结合。大型语言模型（LLM）能够同时执行这两种功能。本课程主要关注NLU方面，特别是如何从自由文本中提取结构化信息。课程中也涉及NLG内容。近期，GPT和Gemini引入了从提示文本中提取结构化输出的能力，并且在2024年11月时，这两个模型是唯一提供此功能的LLM。学员可以通过指定响应架构为Python类，LLM会提供“尽力而为”的响应，尽管有时输出字段可能为空。本课程提供了一种实用和系统的方法，以评估LLM结构化输出响应的准确性。 课程适合人群：本课程适合所有希望利用LLM提取结构化信息的人。如果您在GPT和Gemini API开始支持结构化输出后，曾有以下疑问，则更应考虑参加本课程： 1. 将架构指定为Python类是否真的有效？（是的，但有一些限制） 2. 哪个API表现更好？（可能有） 3. 如何设计Python类以提供更准确的响应？（答案可能会让您惊讶） 4. 这是否意味着提示工程不再重要？（对于这个特定用例来说，它的重要性正在降低） 生物医学NLP：尽管我没有生物医学背景，但我在一项志愿项目中花费了两年时间，成功使用实用的NLP工具从一个流行的生物医学数据集中提取信息。作为学员，您不需要有生物医学背景，但对该主题的兴趣会有所帮助。
Natural Language Processing (NLP) is often* considered to be the combination of two branches of study - Natural Language Understanding (NLU) and Natural Language Generation (NLG). *For example, that is how Ines Montani, co-founder of spaCy recently described the fields in a podcast interview. Large Language Models can do both NLU and NLG. In this course we are primarily interested in the NLU aspect - more specifically we are interested in how to extract structured information from free form text. (There is also an NLG aspect to the course which you will notice as you watch the video lessons).Recently both GPT and Gemini introduced the ability to extract structured output from the prompt text. As of this writing (November 2024), they are the only LLMs which provide native support for this feature via their API itself - in other words, you can simply specify the response schema as a Python class, and the LLMs will give you a "best effort" response which is guaranteed to follow the schema. It is best effort because while the response is guaranteed to follow the schema, sometimes the fields are empty. This course provides a practical and systematic approach for assessing the accuracy of LLM Structured Output responses. Who should take this course?Everyone who is interested in extracting structured information using LLMs can benefit from taking this course. And specifically, you should take this course if you have asked yourself any of the following questions after GPT and Gemini APIs started supporting Structured Outputs:1 Does specifying the schema as a Python class actually work? (Yes, but there are some limitations)2 Is one of the APIs better than the other? (Probably)3 Can you design your Python class in a way which provides more accurate responses? (you might be surprised to find the answer to this)4 Does this mean prompt engineering is not necessary anymore? (It is becoming less important for this particular use case)Biomedical NLPNote: I do NOT have a background in biomedicine, but I have now spent over two years on a volunteer project which requires the use of practical NLP tools to extract information from a popular biomedical dataset and have done so quite successfully.As a student, you do not need to have a background in biomedicine either to complete this course, but it does help if you have an interest in the subject.
