Archives/Prompt-Engineering-Guide
2
0
Fork 0
mirror of https://github.com/dair-ai/Prompt-Engineering-Guide synced 2024-11-10 01:13:36 +00:00
Code Issues Packages Projects Releases Wiki Activity
db0a0c0c98
Prompt-Engineering-Guide/pages/models/chatgpt.ru.mdx

294 lines
31 KiB
Plaintext
Raw Normal View History

added some pages
2023-06-04 17:35:11 +00:00
# Промпт инжиниринг в ChatGPT
import { Callout, FileTree } from 'nextra-theme-docs'
import {Screenshot} from 'components/screenshot'
import CHATGPT1 from '../../img/chatgpt-1.png'
import CHATGPTCLASSIC from '../../img/chatgpt-classic.png'
В данном разделе мы освещаем последние методы инженерии для ChatGPT, включая рекомендации, применение, ограничения, научные статьи и дополнительные материалы для чтения.
<Callout emoji="⚠️">
Данный раздел находится в активной стадии разработки.
</Callout>
Темы:
- [Введение в ChatGPT](#введение-в-chatgpt)
- [Обзор задачи диалогов](#обзор-задачи-диалогов)
- [Диалоги с ChatGPT](#диалоги-с-chatgpt)
---
## Введение в ChatGPT
ChatGPT - это новая модель [обученная OpenAI](https://openai.com/blog/chatgpt), обладающая способностью вести беседу. Эта модель обучена следовать инструкциям в запросе, чтобы предоставлять соответствующие ответы в контексте диалога. ChatGPT может помочь в ответах на вопросы, предлагать рецепты, писать тексты в определенном стиле, генерировать код и многое другое.
ChatGPT обучается с помощью обратной связи с подкреплением от людей (RLHF). Несмотря на то, что эта модель гораздо более мощная, чем предыдущие итерации GPT (и также обучена с целью снизить вредные и неправдивые результаты), у нее всё же есть свои ограничения. Давайте рассмотрим некоторые возможности и ограничения на конкретных примерах.
Вы можете использовать пользовательскую версию ChatGPT [здесь](chat.openai.com), но для приведенных ниже примеров мы будем использовать режим `Chat` на OpenAI Playground.
---
## Обзор задачи диалогов
В одном из предыдущих гайдов мы кратко рассмотрели возможности диалога и роль инструкций: как научить модель вести беседу в определенном стиле, с определенным намерением, поведением и идентичностью.
Давайте вспомним наш предыдущий базовый пример, в котором мы создали систему для ведения беседы, способную генерировать более технические и научные ответы на вопросы.
*Промпт:*
```
The following is a conversation with an AI research assistant. The assistant tone is technical and scientific.
Human: Hello, who are you?
AI: Greeting! I am an AI research assistant. How can I help you today?
Human: Can you tell me about the creation of black holes?
AI:
```
Из приведенного примера видно две важные составляющие:
- **намерение** или объяснение того, что представляет собой чат-бот
- **идентичность**, которая определяет стиль или тональность, с которой чат-бот будет отвечать
Простой пример выше хорошо работает с использованием API для заполнения текста, использующего `text-davinci-003`. Недавно OpenAI [анонсировала API ChatGPT](https://openai.com/blog/introducing-chatgpt-and-whisper-apis), который представляет собой более мощную и экономичную модель `gpt-3.5-turbo`, специально созданную для такого типа функциональности (завершения диалогов). Фактически, OpenAI рекомендует ее как свою лучшую модель даже для случаев использования, не связанных с чатом. Другие преимущества использования API ChatGPT - значительное снижение стоимости (на 90%) и повышение эффективности.
Крупные компании, такие как Snap Inc. и Instacart, уже интегрируют возможности диалога, основанные на ChatGPT, в свои продукты, от персонализированных рекомендаций до открытых целей покупок.
---
## Диалоги с ChatGPT
### Диалоги с несколькими ходами
Чтобы продемонстрировать возможности ChatGPT, мы воспользуемся примером беседы с ассистентом-чатботом, приведенным выше, и обсудим результаты. В отличие от `text-davinci-003`, модель `gpt-3.5-turbo`, на которой работает ChatGPT, использует формат диалога в качестве входных данных. Модель ожидает серию сообщений на входе и использует их для генерации ответа.
*Входные данные:*
```
SYSTEM: You are an AI research assistant. You use a tone that is technical and scientific.
USER: Hello, who are you?
ASSISTANT: Greeting! I am an AI research assistant. How can I help you today?
USER: Can you tell me about the creation of black holes?
```
*Результат:*
```
ASSISTANT: Of course! Black holes are created when a massive star runs out of fuel and collapses under its own gravity. This collapse causes the star to become incredibly dense, with a gravitational field so strong that not even light can escape it. This point of no return is known as the event horizon. Once a star crosses the event horizon, it is considered a black hole...
```
Обратите внимание, что в приведенном выше примере я упростил входные и выходные данные, но для API завершения диалогов ChatGPT требуется, чтобы сообщения были в определенном формате. Я добавил ниже скриншот того, как будет выглядеть этот пример при использовании режима `Chat` на OpenAI Playground:
<Screenshot src={CHATGPT1} alt="CHATGPT1" />
Более формальный вызов API для нашего примера будет выглядеть примерно следующим образом:
```python
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?"}
]
)
```
Фактически, взаимодействие разработчиков с ChatGPT в будущем планируется осуществлять с помощью [языка разметки диалогов](https://github.com/openai/openai-python/blob/main/chatml.md) (ChatML в кратком виде).
### Задачи с одним ходом
Формат диалога позволяет вести многоходовые беседы, но также поддерживает задачи с одним ходом, подобно тому, что мы использовали с `text-davinci-003`. Это означает, что мы можем использовать ChatGPT для выполнения аналогичных задач, как мы продемонстрировали с исходными моделями GPT. Например, попробуем выполнить следующую задачу по ответу на вопрос с использованием ChatGPT:
*Входные данные:*
```
USER: 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:
```
*Результат:*
```
ASSISTANT: Mice.
```
Имейте в виду, что я добавил метки `USER` и `ASSISTANT`, чтобы лучше продемонстрировать, как можно выполнить задачу с использованием ChatGPT. Вот пример с использованием Playground:
<Screenshot src={CHATGPTCLASSIC} alt="CHATGPTCLASSIC" />
Более формально, вот вызов API (я включил только компонент сообщения в запрос):
```python
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,
)
```
### Инструкции для моделей Chat
Согласно официальной документации OpenAI, снимки модели `gpt-3.5-turbo` также будут доступны. Например, мы можем получить снимок от 1 марта `gpt-3.5-turbo-0301`. Это позволяет разработчикам выбирать определенные версии модели. Это также означает, что рекомендации по инструктированию моделей могут меняться от версии к версии.
Текущая рекомендация для `gpt-3.5-turbo-0301` состоит в добавлении инструкций в сообщение от пользователя (`user`), в отличие от доступного сообщения от системы (`system`).
---
## Ссылки
- [Column Type Annotation using ChatGPT](https://arxiv.org/abs/2306.00745) (June 2023)
- [Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions](https://arxiv.org/abs/2306.00551) (June 2023)
- [ChatGPT an ENFJ, Bard an ISTJ: Empirical Study on Personalities of Large Language Models](https://arxiv.org/abs/2305.19926) (May 2023)
- [A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets](https://arxiv.org/abs/2305.18486) (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](https://arxiv.org/abs/2305.18618) (May 2023)
- [GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation](https://arxiv.org/abs/2305.18997) (May 2023)
- [Fairness of ChatGPT](https://arxiv.org/abs/2305.18569) (May 2023)
- [Mapping ChatGPT in Mainstream Media: Early Quantitative Insights through Sentiment Analysis and Word Frequency Analysis](https://arxiv.org/abs/2305.18340) (May 2023)
- [A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions](https://arxiv.org/abs/2305.18339) (May 2023)
- [Do Language Models Know When They're Hallucinating References?](https://arxiv.org/abs/2305.18248) (May 2023)
- [HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis]
- [Playing repeated games with Large Language Models](https://arxiv.org/abs/2305.16867) (May 2023)
- [Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks](https://arxiv.org/abs/2305.16633) (May 2023)
- [Leveraging LLMs for KPIs Retrieval from Hybrid Long-Document: A Comprehensive Framework and Dataset](https://arxiv.org/abs/2305.16344) (May 2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://arxiv.org/abs/2305.18189v1) (May 2023)
- [The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python](https://arxiv.org/pdf/2305.15507v1.pdf) (May 2023)
- [InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language](https://arxiv.org/abs/2305.05662v3) (May 2023)
- [Narrative XL: A Large-scale Dataset For Long-Term Memory Models](https://arxiv.org/abs/2305.13877) (May 2023)
- [Does ChatGPT have Theory of Mind?](https://arxiv.org/abs/2305.14020) (May 2023)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://arxiv.org/abs/2305.03111v2) (May 2023)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://arxiv.org/abs/2305.14196) (May 2023)
- [Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science](https://arxiv.org/abs/2305.14310) (May 2023)
- [ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings](https://arxiv.org/abs/2305.13724) (May 2023)
- [Can LLMs facilitate interpretation of pre-trained language models?](https://arxiv.org/abs/2305.13386) (May 2023)
- [Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding](https://arxiv.org/abs/2305.13512) (May 2023)
- [LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation](https://arxiv.org/abs/2305.13614) (May 2023)
- [ChatGPT as your Personal Data Scientist](https://arxiv.org/abs/2305.13657) (May 2023)
- [Are Large Language Models Good Evaluators for Abstractive Summarization?](https://arxiv.org/abs/2305.13091) (May 2023)
- [Can ChatGPT Defend the Truth? Automatic Dialectical Evaluation Elicits LLMs' Deficiencies in Reasoning](https://arxiv.org/abs/2305.13160) (May 2023)
- [Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection](https://arxiv.org/abs/2305.13276) (May 2023)
- [ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness](https://arxiv.org/abs/2305.12947) (May 2023)
- [Distilling ChatGPT for Explainable Automated Student Answer Assessment](https://arxiv.org/abs/2305.12962) (May 2023)
- [Prompt ChatGPT In MNER: Improved multimodal named entity recognition method based on auxiliary refining knowledge from ChatGPT](https://arxiv.org/abs/2305.12212) (May 2023)
- [ChatGPT Is More Likely to Be Perceived as Male Than Female](https://arxiv.org/abs/2305.12564) (May 2023)
- [Observations on LLMs for Telecom Domain: Capabilities and Limitations](https://arxiv.org/abs/2305.13102) (May 2023)
- [Bits of Grass: Does GPT already know how to write like Whitman?](https://arxiv.org/abs/2305.11064) (May 2023)
- [Are Large Language Models Fit For Guided Reading?](https://arxiv.org/abs/2305.10645) (May 2023)
- [ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages](https://arxiv.org/abs/2305.10510) (May 2023)
- [BAD: BiAs Detection for Large Language Models in the context of candidate screening](https://arxiv.org/abs/2305.10407) (May 2023)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://arxiv.org/abs/2305.10250) (May 2023)
- [Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs](https://arxiv.org/abs/2305.09858) (May 2023)
- [A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions](https://arxiv.org/abs/2305.09402) (May 2023)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://arxiv.org/abs/2304.06588) (April 2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://arxiv.org/abs/2304.05613) (April 2023)
- [Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis](https://arxiv.org/abs/2304.05534) (April 2023)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://arxiv.org/abs/2304.05454) (April 2023)
- [Can ChatGPT and Bard Generate Aligned Assessment Items? A Reliability Analysis against Human Performance](https://arxiv.org/abs/2304.05372) (April 2023)
- [Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding](https://arxiv.org/abs/2304.05368) (April 2023)
- [The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges](https://arxiv.org/abs/2304.05351) (April 2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://arxiv.org/abs/2304.05335) (April 2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://arxiv.org/abs/2304.05197) (April 2023)
- [Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study](https://arxiv.org/abs/2304.04339) (April 2023)
- [A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding](https://arxiv.org/abs/2304.04256) (April 2023)
- [Extractive Summarization via ChatGPT for Faithful Summary Generation](https://arxiv.org/abs/2304.04193) (April 2023)
- [What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory](https://arxiv.org/abs/2304.03612) (April 2023)
- [On the Evaluations of ChatGPT and Emotion-enhanced Prompting for Mental Health Analysis](https://arxiv.org/abs/2304.03347) (April 2023)
- [ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about](https://arxiv.org/abs/2304.03325) (April 2023)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://arxiv.org/abs/2304.03738) (April 2023)
- [Synthesis of Mathematical programs from Natural Language Specifications](https://arxiv.org/abs/2304.03287) (April 2023)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://arxiv.org/abs/2304.03245) (April 2023)
- [Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media](https://arxiv.org/abs/2304.03087) (April 2023)
- [ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model](https://arxiv.org/abs/2304.03086) (April 2023)
- [Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions](https://arxiv.org/abs/2304.02868) (April 2023)
- [Human-like Summarization Evaluation with ChatGPT](https://arxiv.org/abs/2304.02554) (April 2023)
- [Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification](https://arxiv.org/abs/2304.02496) (April 2023)
- [Comparative Analysis of CHATGPT and the evolution of language models](https://arxiv.org/abs/2304.02468) (April 2023)
- [Unleashing the Power of ChatGPT for Translation: An Empirical Study](https://arxiv.org/abs/2304.02182) (April 2023)
- [Geotechnical Parrot Tales (GPT): Overcoming GPT hallucinations with prompt engineering for geotechnical applications](https://arxiv.org/abs/2304.02138) (April 2023)
- [Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing](https://arxiv.org/abs/2304.02017) (April 2023)
- [Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models](https://arxiv.org/abs/2304.01852) (April 2023)
- [Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation](https://arxiv.org/abs/2304.01746) (April 2023)
- [Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT](https://arxiv.org/abs/2304.01246) (April 2023)
- [Large language models can rate news outlet credibility](https://arxiv.org/abs/2304.00228) (April 2023)
- [Can AI Chatbots Pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) Structural Exams?](https://arxiv.org/abs/2303.18149) (April 2023)
- [Can AI Put Gamma-Ray Astrophysicists Out of a Job?](https://arxiv.org/abs/2303.17853) (March 2023)
- [Comparing Abstractive Summaries Generated by ChatGPT to Real Summaries Through Blinded Reviewers and Text Classification Algorithms](https://arxiv.org/abs/2303.17650) (March 2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace](https://arxiv.org/abs/2303.17580) (March 2023)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://arxiv.org/abs/2303.17395) (March 2023)
- [How well do Large Language Models perform in Arithmetic tasks?](https://arxiv.org/abs/2304.02015) (March 2023)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://arxiv.org/abs/2303.17466) (March 2023)
- [Yes but.. Can ChatGPT Identify Entities in Historical Documents?](https://arxiv.org/abs/2303.17322) (March 2023)
- [Evaluation of ChatGPT for NLP-based Mental Health Applications](https://arxiv.org/abs/2303.15727) (March 2023)
- [A Perspectival Mirror of the Elephant: Investigating Language Bias on Google, ChatGPT, Wikipedia, and YouTube](https://arxiv.org/abs/2303.16281) (March 2023)
- [ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools](https://arxiv.org/abs/2303.16352) (March 2023)
- [Zero-shot Clinical Entity Recognition using ChatGPT](https://arxiv.org/abs/2303.16416) (March 2023)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://arxiv.org/abs/2303.16421) (March 2023)
- [ChatGPT4PCG Competition: Character-like Level Generation for Science Birds](https://arxiv.org/abs/2303.15662) (March 2023)
- [ChatGPT as a Factual Inconsistency Evaluator for Abstractive Text Summarization](https://arxiv.org/abs/2303.15621) (March 2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://arxiv.org/abs/2303.14524) (March 2023)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://arxiv.org/abs/2303.13547) (March 2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://arxiv.org/abs/2303.13780) (March 2023)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models: A Case Study on ChatGPT](https://arxiv.org/abs/2303.13809) (March 2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://arxiv.org/pdf/2303.15056v1.pdf) (March 2023)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://arxiv.org/abs/2303.13648) (March 2023)
- [ChatGPT and a New Academic Reality: AI-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing](https://arxiv.org/abs/2303.13367) (March 2023)
- [Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs](https://arxiv.org/abs/2303.12810) (March 2023)
- [Is ChatGPT A Good Keyphrase Generator? A Preliminary Study](https://arxiv.org/abs/2303.13001) (March 2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://arxiv.org/abs/2303.11381) (March 2023)
- [Large Language Models Can Be Used to Estimate the Ideologies of Politicians in a Zero-Shot Learning Setting](https://arxiv.org/abs/2303.12057) (March 2023)
- [Chinese Intermediate English Learners outdid ChatGPT in deep cohesion: Evidence from English narrative writing](https://arxiv.org/abs/2303.11812) (March 2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://arxiv.org/abs/2303.10420) (March 2023)
- [ChatGPT as the Transportation Equity Information Source for Scientific Writing](https://arxiv.org/abs/2303.11158) (March 2023)
- [Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential](https://arxiv.org/abs/2303.09038) (March 2023)
- [ChatGPT Participates in a Computer Science Exam](https://arxiv.org/abs/2303.09461) (March 2023)
- [Consistency Analysis of ChatGPT](https://arxiv.org/abs/2303.06273) (Mar 2023)
- [Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research](https://arxiv.org/abs/2303.07304) (Mar 2023)
- [Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification](https://arxiv.org/abs/2303.07142) (March 2023)
- [Seeing ChatGPT Through Students' Eyes: An Analysis of TikTok Data](https://arxiv.org/abs/2303.05349) (March 2023)
- [Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering -- Example of ChatGPT](https://arxiv.org/abs/2303.05352) (Mar 2023)
- [ChatGPT is on the horizon: Could a large language model be all we need for Intelligent Transportation?](https://arxiv.org/abs/2303.05382) (Mar 2023)
- [Making a Computational Attorney](https://arxiv.org/abs/2303.05383) (Mar 2023)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://arxiv.org/abs/2303.04360) (Mar 2023)
- [MenuCraft: Interactive Menu System Design with Large Language Models](https://arxiv.org/abs/2303.04496) (Mar 2023)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://arxiv.org/abs/2303.04226) (Mar 2023)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://arxiv.org/abs/2303.03836)
- [ChatGPT: Beginning of an End of Manual Annotation? Use Case of Automatic Genre Identification](https://arxiv.org/abs/2303.03953) (Mar 2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://arxiv.org/abs/2303.04048) (Mar 2023)
- [Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT](https://arxiv.org/abs/2303.03186) (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](https://arxiv.org/abs/2303.01194) (Mar 2023)
- [How to format inputs to ChatGPT models](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb) (Mar 2023)
- [Can ChatGPT Assess Human Personalities? A General Evaluation Framework](https://arxiv.org/abs/2303.01248) (Mar 2023)
- [Cross-Lingual Summarization via ChatGPT](https://arxiv.org/abs/2302.14229) (Feb 2023)
- [ChatAug: Leveraging ChatGPT for Text Data Augmentation](https://arxiv.org/abs/2302.13007) (Feb 2023)
- [Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness](https://arxiv.org/abs/2302.13793) (Feb 2023)
- [An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)](https://arxiv.org/abs/2302.13814) (Feb 2023)
- [ChatGPT: A Meta-Analysis after 2.5 Months](https://arxiv.org/abs/2302.13795) (Feb 2023)
- [Let's have a chat! A Conversation with ChatGPT: Technology, Applications, and Limitations](https://arxiv.org/abs/2302.13817) (Feb 2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://arxiv.org/abs/2302.12813) (Feb 2023)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://arxiv.org/abs/2302.12095) (Feb 2023)
- [How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study](https://arxiv.org/abs/2302.10916) (Feb 2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://arxiv.org/abs/2302.10198) (Feb 2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://arxiv.org/abs/2302.11382) (Feb 2023)
- [Zero-Shot Information Extraction via Chatting with ChatGPT](https://arxiv.org/abs/2302.10205) (Feb 2023)
- [ChatGPT: Jack of all trades, master of none](https://arxiv.org/abs/2302.10724) (Feb 2023)
- [A Pilot Evaluation of ChatGPT and DALL-E 2 on Decision Making and Spatial Reasoning](https://arxiv.org/abs/2302.09068) (Feb 2023)
- [Netizens, Academicians, and Information Professionals' Opinions About AI With Special Reference To ChatGPT](https://arxiv.org/abs/2302.07136) (Feb 2023)
- [Linguistic ambiguity analysis in ChatGPT](https://arxiv.org/abs/2302.06426) (Feb 2023)
- [ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots](https://arxiv.org/abs/2302.06466) (Feb 2023)
- [What ChatGPT and generative AI mean for science](https://www.nature.com/articles/d41586-023-00340-6) (Feb 2023)
- [Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature](https://arxiv.org/abs/2302.06474) (Feb 2023)
- [Exploring AI Ethics of ChatGPT: A Diagnostic Analysis](https://arxiv.org/abs/2301.12867) (Jan 2023)
- [ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education](https://www.edu.sot.tum.de/fileadmin/w00bed/hctl/_my_direct_uploads/ChatGPT_for_Good_.pdf) (Jan 2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://arxiv.org/abs/2301.01768) (Jan 2023)
- [Techniques to improve reliability - OpenAI Cookbook](https://github.com/openai/openai-cookbook/blob/main/techniques_to_improve_reliability.md)
- [Awesome ChatGPT Prompts](https://github.com/f/awesome-chatgpt-prompts)
- [Introducing ChatGPT](https://openai.com/blog/chatgpt) (Nov 2022)
Reference in New Issue Copy Permalink