Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Summarization module based on KoBART

Borrows code from RankGPT repo to expand LLM reranking to other LLMs (Vicuna) and Prompt generation methods (LRL, etc)

SummVis is an interactive visualization tool for text summarization.

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

LLM as a Chatbot Service

⚡ Building applications with LLMs through composability ⚡

Train transformer language models with reinforcement learning.

LlamaIndex (GPT Index) is a data framework for your LLM applications

Build Python LLM apps in minutes ⚡️

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Forward-Looking Active REtrieval-augmented generation (FLARE)

Improving Dialogue Summarization with Speaker-aware and Topic-aware Contrastive Learning

Repository for our paper: Dynamic Latent Extraction for Abstractive Long-Input Summarization

Evaluation tool for LLM QA chains

Fusion-in-Decoder