This paper surveys different prompt engineering techniques used to improve the performance of large language models on various Natural Language Processing (NLP) tasks. It categorizes these techniques by NLP task, highlights their performance on different datasets, and discusses state-of-the-art methods for specific datasets. The survey covers 44 research papers exploring 39 prompting methods across 29 NLP tasks.
A Github Gist containing a Python script for text classification using the TxTail API
Exploratory data analysis (EDA) is a powerful technique to understand the structure of word embeddings, the basis of large language models. In this article, we'll apply EDA to GloVe word embeddings and find some interesting insights.
The article discusses the integration of Large Language Models (LLMs) and search engines, exploring two themes: Search4LLM, which focuses on enhancing LLMs using search engines, and LLM4Search, which looks at improving search engines with LLMs.
The llmsherpa project provides APIs to accelerate Large Language Model (LLM) projects. It includes features like LayoutPDFReader for PDF text parsing, smart chunking for vector search and Retrieval Augmented Generation, and table analysis. It is open-sourced under Apache 2.0 license.
This article provides a beginner's guide on using Hugging Face Transformers for text summarization. It explains what text summarization is, its uses, and how it can be performed using extractive and abstractive summarization techniques. The article also provides a simple code example using the Hugging Face pipeline for text summarization.
This article explains Retrieval Augmented Generation (RAG), a method to reduce the risk of hallucinations in Large Language Models (LLMs) by limiting the context in which they generate answers. RAG is demonstrated using txtai, an open-source embeddings database for semantic search, LLM orchestration, and language model workflows.
This comprehensive guide will walk you through everything you need to know to master Tabulate and effectively present your data. Learn about formatting options, handling different data types, customizing table appearance, sorting and filtering data, advanced features, practical examples, and best practices.
Reader helps convert any URL into content suitable for LLMs, including automatic image captioning and web search.
The API is split into two functions: 'Read' and 'Search'. Read converts any URL into content suitable for LLMs and returns the LLM-friendly data. Search allows users to input a search query and receives the top five results in a simplified format.
The API is split into two functions: 'Read' and 'Search'. Read converts any URL into content suitable for LLMs and returns the LLM-friendly data. Search allows users to input a search query and receives the top five results in a simplified format.
This tutorial covers fine-tuning BERT for sentiment analysis using Hugging Face Transformers. Learn to prepare data, set up environment, train and evaluate the model, and make predictions.
