An Open-Source Engineering Guide for Prompt-in-context-learning from EgoAlpha Lab.

📝 Papers | ⚡️ Playground | 🛠 Prompt Engineering | 🌍 ChatGPT Prompt ｜ ⛳ LLMs Usage Guide

⭐️ 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, Prompt Engineering, Agent, and Foundation Models.

🎉Playground🎉: Large language models（LLMs）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.

🎉LLMs Usage Guide🎉: The method for quickly getting started with large language models by using LangChain.

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 AIGC;
• Those whose jobs are replaced by AI automation.

💎EgoAlpha: Hello! human👤, are you ready?

Table of Contents

• 📢 News
• 📜 Papers
  • Survey
  • Prompt Engineering
    • Prompt Design
    • Chain of Thought
    • In-context Learning
    • Retrieval Augmented Generation
    • Evaluation & Reliability
  • Agent
  • Multimodal Prompt
  • Prompt Application
  • Foundation Models
• 👨‍💻 LLM Usage
• ✉️ Contact
• 🙏 Acknowledgements

📢 News

☄️ EgoAlpha releases the TrustGPT focuses on reasoning. Trust the GPT with the strongest reasoning abilities for authentic and reliable answers. You can click here or visit the Playgrounds directly to experience it。

• [2024.8.5]

  • Paper: Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting
  • Paper: Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation

• [2024.8.4]

  • Paper: Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs

• [2024.8.3]

  • Paper: Coalitions of Large Language Models Increase the Robustness of AI Agents

• [2024.8.2]

  • Paper: Large-scale AI performance art: 'Humans stop' posting, 17 large models spamming like crazy

• [2024.8.1]

  • Paper: LLM4CP: Adapting Large Language Models for Channel Prediction

• [2024.7.31]

  • Paper: UrbanGPT: Spatio-Temporal Large Language Models

• [2024.7.30]

  • 🔥🔥🔥Apple's AI version of iOS is hot on its first day

• [2024.7.29] -🔥🔥🔥Paper: Wolf: Captioning Everything with a World Summarization Framework

• [2024.7.28]

  • Paper: The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models

• [2024.7.27]

  • 🔥🔥🔥The GPT-4o mini is a power hog and costs nothing to fine-tune for a limited time of 2 months!

• [2024.7.26]

  • Paper: ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema

• [2024.7.25]

  • Paper: The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs

• [2024.7.24]

  • 🔥🔥🔥Open source beats closed source, llama3.1 reaches T0 level

• [2024.7.23]

  • 🔥🔥🔥OpenAI kicks off miniatures bloodbath! Apple's DCLM comes on strong, crushes Mistral 7B full open source

• [2024.7.22]

  • Paper: LLMmap: Fingerprinting For Large Language Models

• [2024.7.21]

  • Paper: SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

• [2024.7.20]

  • Paper: Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

• [2024.7.19]

  • 🔥🔥🔥OpenAI introduces new lightweight quantisation model GPT-4o mini

• [2024.7.18]

  • Mistral AI has just launched its first open source model based on the Mamba2 architecture, Codestral Mamba (7B), specialising in code generation.
  • Paper: Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models

• [2024.7.17]

  • Paper: The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs

• [2024.7.16]

  • 🔥🔥🔥Open Source! The world's largest AI-based model for pathology is here!

• [2024.7.15]

  • 🔥🔥🔥The world's first big open-source model for chip design is born! 5 years to reshape the $500 billion semiconductor industry!
  • Paper: On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments

• [2024.7.14]

  • 🔥🔥🔥The Big Model Authority Test was exposed as a flop! Favouring closed source models such as GPT-4 even more, even the cue words are treated differently
  • Paper: RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

• [2024.7.13]

  • Paper: FairyLandAI: Personalized Fairy Tales utilizing ChatGPT and DALLE-3

• [2024.7.12]

  • Paper: MUSCLE: A Model Update Strategy for Compatible LLM Evolution

• [2024.7.11]

  • 🔥🔥🔥NVIDIA release: PaperData, Data Everywhere:A Guide for Pretraining Dataset Construction

• [2024.7.10]

  • Paper: Multi-Object Hallucination in Vision-Language Models

• [2024.7.9]

  • Paper: Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

• [2024.7.8]

  • Paper: Temporal Grounding of Activities using Multimodal Large Language Models

• [2024.7.7]

  • 🔥🔥🔥WAIC：2024:Only spend 2 minutes, the requirements document into a product, China's large model development artefacts fire WAIC

• [2024.7.6]

  • 🔥🔥🔥 Gemma 2 is the strongest open-source model, surpassing Llama 3!
  • Paper: IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization

• [2024.7.5]

  • Paper: InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

• [2024.7.4]

  • Paper: Cooperative Multi-Agent Deep Reinforcement Learning Methods for UAV-aided Mobile Edge Computing Networks

• [2024.7.3]

  • Paper: TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

• [2024.7.2]

  • Technical Paper: Motion meets Attention: Video Motion Prompts

• [2024.7.1]

  • Paper: Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs 👉 Complete history news 👈

---

📜 Papers

You can directly click on the title to jump to the corresponding PDF link location

Survey

Motion meets Attention: Video Motion Prompts （2024.07.03）

Towards a Personal Health Large Language Model （2024.06.10）

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning （2024.06.10）

Towards Lifelong Learning of Large Language Models: A Survey （2024.06.10）

Towards Semantic Equivalence of Tokenization in Multimodal LLM （2024.06.07）

LLMs Meet Multimodal Generation and Editing: A Survey （2024.05.29）

Tool Learning with Large Language Models: A Survey （2024.05.28）

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models （2024.05.16）

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach （2024.04.24）

A Survey on the Memory Mechanism of Large Language Model based Agents （2024.04.21）

👉Complete paper list 🔗 for "Survey"👈

Prompt Engineering

Prompt Design

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy （2024.06.28）

Dataset Size Recovery from LoRA Weights （2024.06.27）

Dual-Phase Accelerated Prompt Optimization （2024.06.19）

From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries （2024.06.18）

VoCo-LLaMA: Towards Vision Compression with Large Language Models （2024.06.18）

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation （2024.06.18）

The Impact of Initialization on LoRA Finetuning Dynamics （2024.06.12）

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models （2024.06.07）

Cross-Context Backdoor Attacks against Graph Prompt Learning （2024.05.28）

Yuan 2.0-M32: Mixture of Experts with Attention Router （2024.05.28）

👉Complete paper list 🔗 for "Prompt Design"👈

Chain of Thought

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models （2024.06.07）

Cantor: Inspiring Multimodal Chain-of-Thought of MLLM （2024.04.24）

nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States （2024.04.04）

Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models （2024.04.04）

Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought （2024.04.04）

Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models （2024.03.25）

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science （2024.03.21）

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning （2024.03.12）

ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis （2024.03.11）

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought （2024.03.08）

👉Complete paper list 🔗 for "Chain of Thought"👈

In-context Learning

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation （2024.06.18）

The Impact of Initialization on LoRA Finetuning Dynamics （2024.06.12）

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models （2024.06.07）

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning （2024.06.04）

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks （2024.06.04）

Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models （2024.05.28）

Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion （2024.05.19）

MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning （2024.05.19）

Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning （2024.04.25）

Stronger Random Baselines for In-Context Learning （2024.04.19）

👉Complete paper list 🔗 for "In-context Learning"👈

Retrieval Augmented Generation

Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning （2024.06.24）

Enhancing RAG Systems: A Survey of Optimization Strategies for Performance and Scalability （2024.06.04）

Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training （2024.05.31）

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection （2024.05.25）

DocReLM: Mastering Document Retrieval with Language Model （2024.05.19）

UniRAG: Universal Retrieval Augmentation for Multi-Modal Large Language Models （2024.05.16）

ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning （2024.05.07）

REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs （2024.05.03）

Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation （2024.04.10）

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models （2024.04.04）

👉Complete paper list 🔗 for "Retrieval Augmented Generation"👈

Evaluation & Reliability

CELLO: Causal Evaluation of Large Vision-Language Models （2024.06.27）

PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation （2024.06.26）

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models （2024.06.24）

OR-Bench: An Over-Refusal Benchmark for Large Language Models （2024.05.31）

TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models （2024.05.28）

Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models （2024.05.23）

HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models （2024.05.16）

Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark （2024.05.10）

Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models （2024.05.03）

Causal Evaluation of Language Models （2024.05.01）

👉Complete paper list 🔗 for "Evaluation & Reliability"👈

Agent

Cooperative Multi-Agent Deep Reinforcement Learning Methods for UAV-aided Mobile Edge Computing Networks （2024.07.03）

Symbolic Learning Enables Self-Evolving Agents （2024.06.26）

Adversarial Attacks on Multimodal Agents （2024.06.18）

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning （2024.06.14）

Transforming Wearable Data into Health Insights using Large Language Model Agents （2024.06.10）

Neuromorphic dreaming: A pathway to efficient learning in artificial agents （2024.05.24）

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning （2024.05.16）

Learning Multi-Agent Communication from Graph Modeling Perspective （2024.05.14）

Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning （2024.05.09）

Unveiling Disparities in Web Task Handling Between Human and Web Agent （2024.05.07）

👉Complete paper list 🔗 for "Agent"👈

Multimodal Prompt

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output （2024.07.03）

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy （2024.06.28）

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs （2024.06.28）

LLaVolta: Efficient Multi-modal Models via Stage-wise Visual Context Compression （2024.06.28）

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs （2024.06.24）

VoCo-LLaMA: Towards Vision Compression with Large Language Models （2024.06.18）

Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models （2024.06.12）

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models （2024.06.07）

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning （2024.06.04）

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models （2024.05.31）

👉Complete paper list 🔗 for "Multimodal Prompt"👈

Prompt Application

IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization （2024.07.03）

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs （2024.06.28）

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding （2024.06.27）

Adversarial Search Engine Optimization for Large Language Models （2024.06.26）

VideoLLM-online: Online Video Large Language Model for Streaming Video （2024.06.17）

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs （2024.06.14）

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation （2024.06.10）

Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences （2024.06.07）

PaCE: Parsimonious Concept Engineering for Large Language Models （2024.06.06）

Yuan 2.0-M32: Mixture of Experts with Attention Router （2024.05.28）

👉Complete paper list 🔗 for "Prompt Application"👈

Foundation Models

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts （2024.07.03）

Pedestrian 3D Shape Understanding for Person Re-Identification via Multi-View Learning （2024.07.01）

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs （2024.06.28）

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding （2024.06.27）

Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? （2024.06.27）

Efficient World Models with Context-Aware Tokenization （2024.06.27）

The Remarkable Robustness of LLMs: Stages of Inference? （2024.06.27）

ResumeAtlas: Revisiting Resume Classification with Large-Scale Datasets and Large Language Models （2024.06.26）

AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation （2024.06.18）

Unveiling Encoder-Free Vision-Language Models （2024.06.17）

👉Complete paper list 🔗 for "Foundation Models"👈

👨‍💻 LLM Usage

Large language models (LLMs) are becoming a revolutionary technology that is shaping the development of our era. Developers can create applications that were previously only possible in our imaginations by building LLMs. However, using these LLMs often comes with certain technical barriers, and even at the introductory stage, people may be intimidated by cutting-edge technology: Do you have any questions like the following?

• ❓ How can LLM be built using programming?
• ❓ How can it be used and deployed in your own programs?

💡 If there was a tutorial that could be accessible to all audiences, not just computer science professionals, it would provide detailed and comprehensive guidance to quickly get started and operate in a short amount of time, ultimately achieving the goal of being able to use LLMs flexibly and creatively to build the programs they envision. And now, just for you: the most detailed and comprehensive Langchain beginner's guide, sourced from the official langchain website but with further adjustments to the content, accompanied by the most detailed and annotated code examples, teaching code lines by line and sentence by sentence to all audiences.

Click 👉here👈 to take a quick tour of getting started with LLM.

✉️ 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.