ChatGPT提示工程
在本节中,我们将介绍ChatGPT的最新提示工程技术,包括提示、应用、限制、论文和其他阅读材料。
主题:
ChatGPT简介
ChatGPT是由OpenAI训练的一种新模型,具有交互式对话的能力。该模型经过训练,可以按照提示中的指示,在对话的上下文中提供适当的响应。ChatGPT可以帮助回答问题、建议食谱、以特定风格写歌词、生成代码等等。
ChatGPT使用人类反馈的强化学习(RLHF)进行训练。虽然这个模型比以前的GPT迭代要强大得多(并且还经过了训练以减少有害和不真实的输出),但它仍然有一些限制。让我们通过具体的例子来了解一些能力和限制。
您可以在这里使用ChatGPT的研究预览,但在下面的示例中,我们将使用OpenAI Playground上的“Chat”模式。
审查对话任务
在之前的指南中,我们简要介绍了对话能力和角色提示。我们介绍了如何指示LLM以特定的风格、特定的意图、行为和身份进行对话。
让我们回顾一下我们之前的基本示例,其中我们创建了一个对话系统,该系统能够对问题生成更多的技术和科学响应。
提示:
以下是与AI研究助手的对话。助手的语气是专业和科学的。
人:你好,你是谁?
AI:你好!我是AI研究助手。我今天能帮你什么忙吗?
人:你能告诉我黑洞的形成吗?
AI:
从上面的例子中,您可以看到两个重要的组成部分:
- 意图或聊天机器人的解释
- 身份,指示聊天机器人将使用哪种风格或语气进行响应
上面的简单示例适用于使用text-davinci-003
的文本完成API。最近,OpenAI宣布了ChatGPT API (opens in a new tab),这是一个更强大、更便宜的模型,称为gpt-3.5-turbo
,专门为这种功能(聊天完成)而构建。事实上,OpenAI甚至推荐这个模型作为非聊天用例的最佳模型。使用ChatGPT API的其他好处包括显著降低成本(90%)和提高效率。
像Snap Inc.和Instacart这样的大公司已经在其产品中集成了由ChatGPT提供支持的对话功能,这些产品从个性化推荐到开放式购物目标不等。
与ChatGPT的对话
多轮对话
为了开始展示ChatGPT的能力,我们将使用上面的聊天机器人助手示例并讨论结果。与text-davinci-003
相比,驱动ChatGPT的gpt-3.5-turbo
模型使用聊天格式作为输入。该模型期望一系列消息作为输入,并使用这些消息生成响应。
输入:
系统:你是一个AI研究助手。你使用技术和科学的语气。
用户:你好,你是谁?
助手:问候!我是AI研究助手。我今天能帮你什么忙吗?
用户:你能告诉我黑洞的形成吗?
输出:
助手:当一个巨大的恒星耗尽燃料并在自身的引力下坍塌时,就会形成黑洞。这种坍塌使星体变得极其密集,具有极强的引力场,甚至连光都无法逃脱。这个无法逆转的点被称为事件视界。一旦一颗恒星穿过事件视界,它就被认为是一个黑洞...
请注意,在上面的示例中,我简化了输入和输出,但ChatGPT聊天完成API要求消息以特定格式呈现。我在下面添加了一个快照,显示了在OpenAI Playground中使用“Chat Mode”时此示例的外观:

我们示例的更正式API调用将类似于下面的示例:
import openai
openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "You are an AI research assistant. You use a tone that is technical and scientific."},
{"role": "user", "content": "Hello, who are you?"},
{"role": "assistant", "content": "Greeting! I am an AI research assistant. How can I help you today?"},
{"role": "user", "content": "Can you tell me about the creation of black holes?"}
]
)
事实上,未来开发人员与ChatGPT的交互方式预计将通过聊天标记语言 (opens in a new tab)(简称ChatML)完成。
单轮任务
聊天格式支持多轮对话,但它也支持类似于我们使用text-davinci-003
的单轮任务。这意味着我们可以使用ChatGPT执行与我们为原始GPT模型演示的类似任务。例如,让我们尝试使用ChatGPT执行以下问答任务:
输入:
用户:根据下面的上下文回答问题。保持答案简短明了。如果不确定答案,请回答“不确定答案”。
背景:Teplizumab的起源可以追溯到新泽西州的一家名为Ortho Pharmaceutical的药品公司。在那里,科学家们生成了抗体的早期版本,被称为OKT3。最初是从老鼠中提取出来的分子,它能够结合到T细胞表面并限制它们杀伤其他细胞的潜力。1986年,该药物获得批准用于帮助预防肾移植后器官排斥反应,成为第一个允许人类使用的治疗性抗体。
问题:OKT3最初是从哪里提取出来的?
回答:
输出:
助手:老鼠。
请记住,我添加了“用户”和“助手”标签以更好地演示如何使用ChatGPT执行任务。以下是在Playground中使用的示例:

更正式地说,这是API调用(我仅包括请求的消息组件):
CONTENT = """Answer the question based on the context below. Keep the answer short and concise. Respond \"Unsure about answer\" if not sure about the answer.
Context: Teplizumab traces its roots to a New Jersey drug company called Ortho Pharmaceutical. There, scientists generated an early version of the antibody, dubbed OKT3. Originally sourced from mice, the molecule was able to bind to the surface of T cells and limit their cell-killing potential. In 1986, it was approved to help prevent organ rejection after kidney transplants, making it the first therapeutic antibody allowed for human use.
Question: What was OKT3 originally sourced from?
Answer:
"""
response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": CONTENT},
],
temperature=0,
)
指导聊天模型
根据官方OpenAI文档,gpt-3.5-turbo
模型的快照也将提供。例如,我们可以访问3月1日的快照 gpt-3.5-turbo-0301
。这使开发人员可以选择特定的模型版本。这也意味着指导模型的最佳实践可能会从版本到版本发生变化。
对于gpt-3.5-turbo-0301
,当前建议是在“用户”消息中添加说明,而不是可用的“系统”消息。
Notebooks
这里有一个 notebook,可以了解如何使用官方的 openai
库调用 ChatGPT API:
引文
- Column Type Annotation using ChatGPT (opens in a new tab) (June 2023)
- Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions (opens in a new tab) (June 2023)
- ChatGPT an ENFJ, Bard an ISTJ: Empirical Study on Personalities of Large Language Models (opens in a new tab) (May 2023)
- A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets (opens in a new tab) (May 2023)
- Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard (opens in a new tab) (May 2023)
- GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation (opens in a new tab) (May 2023)
- Fairness of ChatGPT (opens in a new tab) (May 2023)
- Mapping ChatGPT in Mainstream Media: Early Quantitative Insights through Sentiment Analysis and Word Frequency Analysis (opens in a new tab) (May 2023)
- A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions (opens in a new tab) (May 2023)
- Do Language Models Know When They're Hallucinating References? (opens in a new tab) (May 2023)
- [HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis]
- Playing repeated games with Large Language Models (opens in a new tab) (May 2023)
- Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks (opens in a new tab) (May 2023)
- Leveraging LLMs for KPIs Retrieval from Hybrid Long-Document: A Comprehensive Framework and Dataset (opens in a new tab) (May 2023)
- Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models (opens in a new tab) (May 2023)
- The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python (opens in a new tab) (May 2023)
- InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language (opens in a new tab) (May 2023)
- Narrative XL: A Large-scale Dataset For Long-Term Memory Models (opens in a new tab) (May 2023)
- Does ChatGPT have Theory of Mind? (opens in a new tab) (May 2023)
- Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (opens in a new tab) (May 2023)
- ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (opens in a new tab) (May 2023)
- Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science (opens in a new tab) (May 2023)
- ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings (opens in a new tab) (May 2023)
- Can LLMs facilitate interpretation of pre-trained language models? (opens in a new tab) (May 2023)
- Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding (opens in a new tab) (May 2023)
- LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation (opens in a new tab) (May 2023)
- ChatGPT as your Personal Data Scientist (opens in a new tab) (May 2023)
- Are Large Language Models Good Evaluators for Abstractive Summarization? (opens in a new tab) (May 2023)
- Can ChatGPT Defend the Truth? Automatic Dialectical Evaluation Elicits LLMs' Deficiencies in Reasoning (opens in a new tab) (May 2023)
- Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection (opens in a new tab) (May 2023)
- ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness (opens in a new tab) (May 2023)
- Distilling ChatGPT for Explainable Automated Student Answer Assessment (opens in a new tab) (May 2023)
- Prompt ChatGPT In MNER: Improved multimodal named entity recognition method based on auxiliary refining knowledge from ChatGPT (opens in a new tab) (May 2023)
- ChatGPT Is More Likely to Be Perceived as Male Than Female (opens in a new tab) (May 2023)
- Observations on LLMs for Telecom Domain: Capabilities and Limitations (opens in a new tab) (May 2023)
- Bits of Grass: Does GPT already know how to write like Whitman? (opens in a new tab) (May 2023)
- Are Large Language Models Fit For Guided Reading? (opens in a new tab) (May 2023)
- ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages (opens in a new tab) (May 2023)
- BAD: BiAs Detection for Large Language Models in the context of candidate screening (opens in a new tab) (May 2023)
- MemoryBank: Enhancing Large Language Models with Long-Term Memory (opens in a new tab) (May 2023)
- Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs (opens in a new tab) (May 2023)
- A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions (opens in a new tab) (May 2023)
- ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning (opens in a new tab) (April 2023)
- ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (opens in a new tab) (April 2023)
- Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis (opens in a new tab) (April 2023)
- Zero-shot Temporal Relation Extraction with ChatGPT (opens in a new tab) (April 2023)
- Can ChatGPT and Bard Generate Aligned Assessment Items? A Reliability Analysis against Human Performance (opens in a new tab) (April 2023)
- Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding (opens in a new tab) (April 2023)
- The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges (opens in a new tab) (April 2023)
- Toxicity in ChatGPT: Analyzing Persona-assigned Language Models (opens in a new tab) (April 2023)
- Multi-step Jailbreaking Privacy Attacks on ChatGPT (opens in a new tab) (April 2023)
- Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study (opens in a new tab) (April 2023)
- A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding (opens in a new tab) (April 2023)
- Extractive Summarization via ChatGPT for Faithful Summary Generation (opens in a new tab) (April 2023)
- What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory (opens in a new tab) (April 2023)
- On the Evaluations of ChatGPT and Emotion-enhanced Prompting for Mental Health Analysis (opens in a new tab) (April 2023)
- ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about (opens in a new tab) (April 2023)
- Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models (opens in a new tab) (April 2023)
- Synthesis of Mathematical programs from Natural Language Specifications (opens in a new tab) (April 2023)
- Large language models effectively leverage document-level context for literary translation, but critical errors persist (opens in a new tab) (April 2023)
- Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media (opens in a new tab) (April 2023)
- ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model (opens in a new tab) (April 2023)
- Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions (opens in a new tab) (April 2023)
- Human-like Summarization Evaluation with ChatGPT (opens in a new tab) (April 2023)
- Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification (opens in a new tab) (April 2023)
- Comparative Analysis of CHATGPT and the evolution of language models (opens in a new tab) (April 2023)
- Unleashing the Power of ChatGPT for Translation: An Empirical Study (opens in a new tab) (April 2023)
- Geotechnical Parrot Tales (GPT): Overcoming GPT hallucinations with prompt engineering for geotechnical applications (opens in a new tab) (April 2023)
- Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing (opens in a new tab) (April 2023)
- Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models (opens in a new tab) (April 2023)
- Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation (opens in a new tab) (April 2023)
- Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT (opens in a new tab) (April 2023)
- Large language models can rate news outlet credibility (opens in a new tab) (April 2023)
- Can AI Chatbots Pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) Structural Exams? (opens in a new tab) (April 2023)
- Can AI Put Gamma-Ray Astrophysicists Out of a Job? (opens in a new tab) (March 2023)
- Comparing Abstractive Summaries Generated by ChatGPT to Real Summaries Through Blinded Reviewers and Text Classification Algorithms (opens in a new tab) (March 2023)
- HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace (opens in a new tab) (March 2023)
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models (opens in a new tab) (March 2023)
- WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research (opens in a new tab) (March 2023)
- How well do Large Language Models perform in Arithmetic tasks? (opens in a new tab) (March 2023)
- Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study (opens in a new tab) (March 2023)
- Yes but.. Can ChatGPT Identify Entities in Historical Documents? (opens in a new tab) (March 2023)
- Evaluation of ChatGPT for NLP-based Mental Health Applications (opens in a new tab) (March 2023)
- A Perspectival Mirror of the Elephant: Investigating Language Bias on Google, ChatGPT, Wikipedia, and YouTube (opens in a new tab) (March 2023)
- ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools (opens in a new tab) (March 2023)
- Zero-shot Clinical Entity Recognition using ChatGPT (opens in a new tab) (March 2023)
- ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models (opens in a new tab) (March 2023)
- ChatGPT4PCG Competition: Character-like Level Generation for Science Birds (opens in a new tab) (March 2023)
- ChatGPT as a Factual Inconsistency Evaluator for Abstractive Text Summarization (opens in a new tab) (March 2023)
- Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System (opens in a new tab) (March 2023)
- A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability (opens in a new tab) (March 2023)
- Towards Making the Most of ChatGPT for Machine Translation (opens in a new tab) (March 2023)
- Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models: A Case Study on ChatGPT (opens in a new tab) (March 2023)
- ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks (opens in a new tab) (March 2023)
- ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark (opens in a new tab) (March 2023)
- ChatGPT and a New Academic Reality: AI-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing (opens in a new tab) (March 2023)
- Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs (opens in a new tab) (March 2023)
- Is ChatGPT A Good Keyphrase Generator? A Preliminary Study (opens in a new tab) (March 2023)
- MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action (opens in a new tab) (March 2023)
- Large Language Models Can Be Used to Estimate the Ideologies of Politicians in a Zero-Shot Learning Setting (opens in a new tab) (March 2023)
- Chinese Intermediate English Learners outdid ChatGPT in deep cohesion: Evidence from English narrative writing (opens in a new tab) (March 2023)
- A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models (opens in a new tab) (March 2023)
- ChatGPT as the Transportation Equity Information Source for Scientific Writing (opens in a new tab) (March 2023)
- Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential (opens in a new tab) (March 2023)
- ChatGPT Participates in a Computer Science Exam (opens in a new tab) (March 2023)
- Consistency Analysis of ChatGPT (opens in a new tab) (Mar 2023)
- Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research (opens in a new tab) (Mar 2023)
- Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification (opens in a new tab) (March 2023)
- Seeing ChatGPT Through Students' Eyes: An Analysis of TikTok Data (opens in a new tab) (March 2023)
- Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering -- Example of ChatGPT (opens in a new tab) (Mar 2023)
- ChatGPT is on the horizon: Could a large language model be all we need for Intelligent Transportation? (opens in a new tab) (Mar 2023)
- Making a Computational Attorney (opens in a new tab) (Mar 2023)
- Does Synthetic Data Generation of LLMs Help Clinical Text Mining? (opens in a new tab) (Mar 2023)
- MenuCraft: Interactive Menu System Design with Large Language Models (opens in a new tab) (Mar 2023)
- A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT (opens in a new tab) (Mar 2023)
- Exploring the Feasibility of ChatGPT for Event Extraction (opens in a new tab)
- ChatGPT: Beginning of an End of Manual Annotation? Use Case of Automatic Genre Identification (opens in a new tab) (Mar 2023)
- Is ChatGPT a Good NLG Evaluator? A Preliminary Study (opens in a new tab) (Mar 2023)
- Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT (opens in a new tab) (Mar 2023)
- UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction (opens in a new tab) (Mar 2023)
- How to format inputs to ChatGPT models (opens in a new tab) (Mar 2023)
- Can ChatGPT Assess Human Personalities? A General Evaluation Framework (opens in a new tab) (Mar 2023)
- Cross-Lingual Summarization via ChatGPT (opens in a new tab) (Feb 2023)
- ChatAug: Leveraging ChatGPT for Text Data Augmentation (opens in a new tab) (Feb 2023)
- Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness (opens in a new tab) (Feb 2023)
- An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP) (opens in a new tab) (Feb 2023)
- ChatGPT: A Meta-Analysis after 2.5 Months (opens in a new tab) (Feb 2023)
- Let's have a chat! A Conversation with ChatGPT: Technology, Applications, and Limitations (opens in a new tab) (Feb 2023)
- Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback (opens in a new tab) (Feb 2023)
- On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective (opens in a new tab) (Feb 2023)
- How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study (opens in a new tab) (Feb 2023)
- Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT (opens in a new tab) (Feb 2023)
- A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT (opens in a new tab) (Feb 2023)
- Zero-Shot Information Extraction via Chatting with ChatGPT (opens in a new tab) (Feb 2023)
- ChatGPT: Jack of all trades, master of none (opens in a new tab) (Feb 2023)
- A Pilot Evaluation of ChatGPT and DALL-E 2 on Decision Making and Spatial Reasoning (opens in a new tab) (Feb 2023)
- Netizens, Academicians, and Information Professionals' Opinions About AI With Special Reference To ChatGPT (opens in a new tab) (Feb 2023)
- Linguistic ambiguity analysis in ChatGPT (opens in a new tab) (Feb 2023)
- ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots (opens in a new tab) (Feb 2023)
- What ChatGPT and generative AI mean for science (opens in a new tab) (Feb 2023)
- Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature (opens in a new tab) (Feb 2023)
- Exploring AI Ethics of ChatGPT: A Diagnostic Analysis (opens in a new tab) (Jan 2023)
- ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education (opens in a new tab) (Jan 2023)
- The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation (opens in a new tab) (Jan 2023)
- Techniques to improve reliability - OpenAI Cookbook (opens in a new tab)
- Awesome ChatGPT Prompts (opens in a new tab)
- Introducing ChatGPT (opens in a new tab) (Nov 2022)