An Open-Source Engineering Guide for Prompt-in-context-learning from EgoAlpha Lab.
📝 Papers | ⚡️ Playground | 🛠 Prompt Engineering | 🌍 ChatGPT Prompt
⭐️ Shining ⭐️: This is fresh, daily-updated resources for in-context learning and prompt engineering. As Artificial General Intelligence (AGI) is approaching, let’s take action and become a super learner so as to position ourselves at the forefront of this exciting era and strive for personal and professional greatness.
The resources include:
🎉Papers🎉: The latest papers about in-context learning or prompt engineering.
🎉Playground🎉: Large language models that enable prompt experimentation.
🎉Prompt Engineering🎉: Prompt techniques for leveraging large language models.
🎉ChatGPT Prompt🎉: Prompt examples that can be applied in our work and daily lives.
In the future, there will likely be two types of people on Earth (perhaps even on Mars, but that's a question for Musk):
- Those who enhance their abilities through the use of AI;
- Those whose jobs are replaced by AI automation.
💎EgoAlpha: Hello! human👤, are you ready?
📢 News
-
[2023.3.21] 🔥🔥🔥Google Bard is now available in the US and UK, w/ more countries to come.
-
[2023.3.20] 💥 OpenAI’s new paper looks at the economical impact of LLMs+Labor Market.GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models
-
[2023.3.17] Microsoft 365 Copilot released. Word, Excel, PowerPoint, Outlook powered by LLMs.
-
[2023.3.16] Baidu announcing the LLM named "文心一言"(ERNIE3.0 + PLATO)
-
[2023.3.15] Two Breaking News:
-
[2023.3.13] LLaMA has been fine-tuned by Stanford
-
[2023.3.10] Announcing OpenChatKit by Together
📜 Papers
You can directly click on the title to jump to the corresponding PDF link location
Survey
Augmented Language Models: a Survey （2023.02.15）
A Survey for In-context Learning （2022.12.31）
Towards Reasoning in Large Language Models: A Survey （2022.12.20）
Reasoning with Language Model Prompting: A Survey （2022.12.19）
Emergent Abilities of Large Language Models （2022.06.15）
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing （2021.07.28）
👉Complete paper list 🔗 for "Survey"👈
Prompt Engineering
📌 Prompt Design
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT （2023.02.21）
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks （2023.02.16）
Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation （2023.02.02）
Progressive Prompts: Continual Learning for Language Models （2023.01.29）
Batch Prompting: Efficient Inference with Large Language Model APIs （2023.01.19）
Promptagator: Few-shot Dense Retrieval From 8 Examples （2022.09.23）
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models （2022.08.16）
DocPrompting: Generating Code by Retrieving the Docs （2022.07.13）
Design Guidelines for Prompt Engineering Text-to-Image Generative Models （2021.09.14）
Program Synthesis with Large Language Models （2021.08.16）
👉Complete paper list 🔗 for "Prompt Design"👈
📌 Automatic Prompt
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data （2023.02.24）
Guiding Large Language Models via Directional Stimulus Prompting （2023.02.22）
Evaluating the Robustness of Discrete Prompts （2023.02.11）
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery （2023.02.07）
Making Pre-trained Language Models Better Few-shot Learners （2021.01.01）
Eliciting Knowledge from Language Models Using Automatically Generated Prompts （2020.10.29）
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification （2020.10.26）
👉Complete paper list 🔗 for "Automatic Prompt"👈
📌 Chain of Thought
Active Prompting with Chain-of-Thought for Large Language Models （2023.02.23）
Multimodal Chain-of-Thought Reasoning in Language Models （2023.02.02）
Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models （2023.02.01）
Faithful Chain-of-Thought Reasoning （2023.01.31）
Large Language Models Are Reasoning Teachers （2022.12.20）
The Impact of Symbolic Representations on In-context Learning for Few-shot Reasoning （2022.12.16）
Complementary Explanations for Effective In-Context Learning （2022.11.25）
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them （2022.10.17）
Prompting GPT-3 To Be Reliable （2022.10.17）
Automatic Chain of Thought Prompting in Large Language Models （2022.10.07）
👉Complete paper list 🔗 for "Chain of Thought"👈
📌 Knowledge Augmented Prompts
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT （2023.02.21）
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks （2023.02.16）
Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation （2023.02.02）
Progressive Prompts: Continual Learning for Language Models （2023.01.29）
Batch Prompting: Efficient Inference with Large Language Model APIs （2023.01.19）
Promptagator: Few-shot Dense Retrieval From 8 Examples （2022.09.23）
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models （2022.08.16）
DocPrompting: Generating Code by Retrieving the Docs （2022.07.13）
Design Guidelines for Prompt Engineering Text-to-Image Generative Models （2021.09.14）
Program Synthesis with Large Language Models （2021.08.16）
👉Complete paper list 🔗 for "Knowledge Augmented Prompts"👈
📌 Evaluation & Reliability
Language Model Crossover: Variation through Few-Shot Prompting （2023.02.23）
Evaluating the Robustness of Discrete Prompts （2023.02.11）
PLACES: Prompting Language Models for Social Conversation Synthesis （2023.02.07）
Controlling for Stereotypes in Multimodal Language Model Evaluation （2023.02.03）
Large Language Models Can Be Easily Distracted by Irrelevant Context （2023.01.31）
Emergent Analogical Reasoning in Large Language Models （2022.12.19）
Discovering Language Model Behaviors with Model-Written Evaluations （2022.12.19）
On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning （2022.12.15）
Solving math word problems with process- and outcome-based feedback （2022.11.25）
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks （2022.11.22）
👉Complete paper list 🔗 for "Evaluation & Reliability"👈
In-context Learning
Larger language models do in-context learning differently （2023.03.07）
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks （2023.03.01）
Language Model Crossover: Variation through Few-Shot Prompting （2023.02.23）
How Does In-Context Learning Help Prompt Tuning? （2023.02.22）
Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints （2023.02.17）
Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning （2023.01.27）
Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning （2023.01.27）
One Embedder, Any Task: Instruction-Finetuned Text Embeddings （2022.12.19）
Complementary Explanations for Effective In-Context Learning （2022.11.25）
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them （2022.10.17）
👉Complete paper list 🔗 for "In-context Learning"👈
Multimodal Prompt
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models （2023.03.08）
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning （2023.03.06）
Multimodal Chain-of-Thought Reasoning in Language Models （2023.02.02）
CoHOZ: Contrasive Multimodal prompt Tuning for Hierarchical Open-set Zero-shot Recognition （2022.10.10）
VIMA: General Robot Manipulation with Multimodal Prompts （2022.10.06）
Learning to Prompt for Vision-Language Models （2022.09.01）
Visual Prompt Tuning （2022.03.23）
Multimodal Few-Shot Learning with Frozen Language Models （2021.06.25）
Similarity-Aware Multimodal Prompt Learning for Fake News Detection
👉Complete paper list 🔗 for "Multimodal Prompt"👈
Prompt Application
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks （2023.03.01）
Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis （2023.03.01）
EvoPrompting: Language Models for Code-Level Neural Architecture Search （2023.02.28）
Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales （2023.02.17）
LabelPrompt: Effective Prompt-based Learning for Relation Classification （2023.02.16）
Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition （2023.02.16）
Prompting for Multimodal Hateful Meme Classification （2023.02.08）
QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition （2022.03.03）
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting （2021.08.31）
👉Complete paper list 🔗 for "Prompt Application"👈
Foundation Models
Meet in the Middle: A New Pre-training Paradigm （2023.03.13）
High-throughput Generative Inference of Large Language Models with a Single GPU （2023.03.13）
Stabilizing Transformer Training by Preventing Attention Entropy Collapse （2023.03.11）
An Overview on Language Models: Recent Developments and Outlook （2023.03.10）
Foundation Models for Decision Making: Problems, Methods, and Opportunities （2023.03.07）
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding （2023.03.07）
LLaMA: Open and Efficient Foundation Language Models （2023.02.27）
Self-Instruct: Aligning Language Model with Self Generated Instructions （2022.12.20）
PaLM: Scaling Language Modeling with Pathways （2022.04.05）
LoRA: Low-Rank Adaptation of Large Language Models （2021.06.17）
👉Complete paper list 🔗 for "Foundation Models"👈
✉️ Contact
This repo is maintained by EgoAlpha Lab. Questions and discussions are welcome via helloegoalpha@gmail.com.
We are willing to engage in discussions with friends from the academic and industrial communities, and explore the latest developments in prompt engineering and in-context learning together.
🙏 Acknowledgements
Thanks to the PhD students from EgoAlpha Lab and other workers who participated in this repo. We will improve the project in the follow-up period and maintain this community well. We also would like to express our sincere gratitude to the authors of the relevant resources. Your efforts have broadened our horizons and enabled us to perceive a more wonderful world.