AI Personal Learning
and practical guidance
讯飞绘镜

AI knowledge Page 10

什么是 Transformer?-首席AI分享圈

What is Transformer?

  Transformer is a deep learning modeling architecture for Natural Language Processing (NLP), proposed by Vaswani et al. in 2017. It is mainly used for processing sequence-to-sequence tasks, such as machine translation, text generation, and so on. Briefly, the original Transformer model for text generation...

COT及相关高级提示变种提示词讲解-首席AI分享圈

COT and related advanced cue variants cue words explained

DISCLAIMER: While basic hinting techniques (e.g., zero/few sample examples or imperative hints) are very efficient, more sophisticated hints may be more effective when faced with some complex puzzles (e.g., math/programming or problems requiring multi-step logical reasoning). Since Large Language Models (LLMs) deal with such problems...

ChatGPT Prompts Level 10 Tips: From Novice to Expert

I've invested a lot of time researching and testing various cues to find the best results. In this video, I've summarized all these experiences into 10 levels of cue word design techniques. We'll start with the basics and go all the way down to the expert techniques that won the recent Singapore Prompter Design Competition. Then we...

List of common words used by Agent

How to water a thesis? Choose Agent-related propositions, add the following inspirations to React for experimentation, and work backwards to the argument based on the results, which will generally yield some results. Information Perception English Chinese Chinese Explanation Perception refers to the process of acquiring information about the environment through the senses, which encompasses...

提示工程在大语言模型中应用的必要性-首席AI分享圈

The Need for Cue Engineering in Large Language Modeling

The following focuses on the basic idea of hint engineering and how it can improve the performance of the Large Language Model (LLM)... Interfaces for LLM: One of the key reasons why large language models are so hot is that their text-to-text interfaces enable a minimalist operational experience. In the past, solving tasks using deep learning typically required...

MemGPT项目:在对话中保持长记忆-首席AI分享圈

The MemGPT program: keeping long memories in conversation

Open source address: https://github.com/cpacker/MemGPT Thesis address: https://arxiv.org/abs/2310.08560 Official website: https://memgpt.ai/ MemGPT supports: 1. Management of long-term memory or state 2. Linking of RAG-based technologies External data sources 3.

SEO for Beginners Guide

This beginner's guide consists of seven chapters that contain everything you need to understand the basics of SEO and start improving your rankings. You'll also find links to helpful resources on our SEO blog and YouTube channel so you can build your own path to SEO savvy . 1/ How Search Engines Work...

Evaluating the Impact of Large-scale Language Modeling (LLM) on Knowledge Workers

Original article: https://www.hbs.edu/ris/PublicationFiles/24-013_d9b45b68-9e74-42d6-a1c6-c72fb70c7282.pdf The purpose of this paper is to explore the impact of artificial intelligence on the productivity and quality of knowledge workers, with field experiments Drawing conclusions. The research team includes researchers from ha...

多样本(示例)越狱攻击-首席AI分享圈

Multibook (example) jailbreak attack

Researchers have investigated a "jailbreak attack" technique - a method that can be used to bypass security fences set up by developers of large language models (LLMs). The technique, known as the "multisample jailbreak attack," works on Anthropic's own models as well as those produced by other AI companies. The researchers pre...

ReAct: 大语言模型中推理和行动协同工作-首席AI分享圈

ReAct: Reasoning and Action Working Together in Large Language Models

Original: https://arxiv.org/pdf/2210.03629.pdf Can't understand how ReAct works and applies even after reading it? See ReAct Implementation Logic in Practice with real-world examples. Abstract Although large-scale language models (LLMs) are useful in the tasks of language understanding and interactive decision...

RAG:检索增强-首席AI分享圈

RAG: Retrieval Augmentation

RAG (Retrieve Augmented Generation) is a technique for optimizing the output of Large Language Models (LLMs) based on authoritative knowledge base information. This technique extends the functionality of LLMs to refer to the internal knowledge base of a particular domain or organization when generating responses to...

Proposition Retrieval:命题检索-首席AI分享圈

Proposition Retrieval

Original text: "Dense X Retrieval: What Retrieval Granularity Should We Use?" Note: This method is suitable for a small number of models, such as the OPENAI series, the Claude series, Mixtral, Yi, and qwen. Abstract In open-domain natural language processing (NLP) tasks, ...

一种新的 Prompt 方法——“类推提示法”(Analogical Prompting)-首席AI分享圈

A new approach to Prompting - Analogical Prompting

Today I read an interesting paper "Large Language Models as Analogical Reasoners", which mentions a new approach to Prompt - "Analogical Prompting. If you are familiar with prompt engineering, you must have heard of "Chain of Thought" (CoT), which is an analogical method of prompting...

BoT:强化思考:用大型语言模型解决试错问题-首席AI分享圈

BoT: Enhanced Thinking: Solving Trial and Error Problems with Large Language Models

Abstract The reasoning performance of Large Language Models (LLMs) on a wide range of problems relies heavily on chained-thinking prompts, which involves providing a number of chained-thinking demonstrations as exemplars in the prompts. Recent research, e.g., thinking trees, has pointed to exploration and self-assessment of reasoning in complex problem solving ...

Intents : Explain with zep how to make a big model understand customer intents.

In Natural Language Processing (NLP), intent refers to a user's expression of some purpose, want or desire. By analyzing the messages sent by the user and recognizing the intention behind them, we can reply with relevant content. For example, "order food", "check the weather", "I want to go to Paris" are all valid intents. In order for chatbots to...

en_USEnglish