RoleLLM

Role-playing framework for large language models

CommonProductEntertainmentNatural Language ProcessingRole-Playing

RoleLLM is a role-playing framework designed to build and evaluate the role-playing capabilities of large language models. It consists of four stages: role summary construction, context-based instruction generation, role prompting using GPT, and role-based instruction adjustment. Through Context-Instruct and RoleGPT, we created RoleBench, a systematic and fine-grained role-level benchmark dataset containing 168,093 samples. Moreover, RoCIT achieved significant improvements in role-playing ability on RoleBench, producing RoleLLaMA (English) and RoleGLM (Chinese), even comparable to results obtained with GPT-4-based RoleGPT.

Best AI Websites & Tools

RoleLLM

RoleLLM Visit Over Time

RoleLLM Visit Trend

RoleLLM Visit Geography

RoleLLM Traffic Sources

RoleLLM Alternatives

awesome-LLM-resources — A comprehensive collection of global large language model resources.

OneGen — An efficient single-pass unified generation and retrieval framework suitable for large language models.

LongCite — Generates fine-grained citations for large language models in long text question answering.

iText2KG — Incrementally build knowledge graphs using large language models.

MedTrinity-25M — A large-scale multimodal medical dataset

Data-Juicer — A one-stop data processing system that provides high-quality data for large language models.

DCLM-baseline — High-performance language model benchmark dataset

Index-1.9B — Index-1.9B is a lightweight, open-source large language model developed independently by Bilibili.

emo-visual-data — Emoji Visual Annotation Dataset

Models Table — A comprehensive list and information about large language models

FlashRAG — Efficient Toolkit for Retrieval-Augmented Generation Research

ImageInWords — A model for generating highly detailed image descriptions, designed for training visual language models.

WildChat — A corpus composed of real-world user interactions with ChatGPT.

FineWeb — High-quality English webpage dataset

MNBVC — MNBVC is a massive Chinese corpus comparable to the 40T data used to train ChatGPT.

BrainSoup — Build your AI team that works for you

En3D — 3D Character Generation Model

LLM Maybe LongLM — Extends the context window of large language models

Distil-Whisper — A collection of models and datasets.

I2VGen-XL — AI Model Library and Dataset Platform

Inst-Inpaint — An image restoration algorithm based on natural language input

MobileLLM-350M — An efficiently optimized language model with sub-billion parameters, specifically designed for device-side applications.

xAI API — API for Grok series foundational models available for developers.

Data Formulator — AI-powered data visualization tool

Stagehand — An AI-driven web browsing framework focused on simplicity and scalability.

URL Parser Online — An online URL parser that converts URLs into a format suitable for large language models.

SELA — SELA enhances automated machine learning by combining Monte Carlo Tree Search and LLM-based agents.

ChatGPT Search — Get quick and timely answers through natural language searches.

LongRAG — Enhanced Retrieval-Augmented Generation Model for Long-Text Question Answering