factool
FacTool: Factuality Detection in Generative AI (by GAIR-NLP)
chatarena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs. (by Farama-Foundation)
| factool | chatarena | |
|---|---|---|
| 1 | 6 | |
| 775 | 1,276 | |
| 0.4% | 4.5% | |
| 7.3 | 8.4 | |
| 8 months ago | 20 days ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
factool
Posts with mentions or reviews of factool.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2024-05-03.
-
How to Detect AI Hallucinations
FACTOOL is a task and domain-agnostic framework designed to tackle the escalating challenge of factual error detection in generative AI. It is a five-step tool-augmented framework that consists of claim extraction, query generation, tool querying, evidence collection, and verification. FACTOOL uses tools like Google Search, Google Scholar, code interpreters, Python, and even LLMs themselves to detect factual errors in knowledge-based QA, code generation, math problem solving, and scientific literature review writing. It outperforms all other baselines across all scenarios and is shown to be highly robust in performing its specified tasks compared to LLMs themselves.
chatarena
Posts with mentions or reviews of chatarena.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-07-10.
- ChatArena – Building Multi-Agent Environments for LLMs
-
Is it possible to make two LLMs talk to each other?
www.chatarena.org you're welcome
-
Making a custom Google Translate equivalent / web translation filter for my conlang?
My eventual goal: An artificial friend group, or rather, a multi-agent LLM system, similar to ChatArena. I wouldn't need the smartest AI friends, as long as I could simulate cross-directional conversation in my conlang in an artificial native speaker environment. Eventually, perhaps I could interact with these artificial friends in a PC or VR gaming setting. I could do a gaming stream and speak only in my conlang, with conlang-speaking AI friends as co-hosts. Regardless if there is an audience or not, this would be an excellent way to practice my conlang on an intuitive level.
- Multi-Agent Language Game Environments for LLMs
-
🏟 Meet ChatArena: A Python Library Designed To Facilitate Communication And Collaboration Between Multiple Large Language Models (LLMs)
Github: https://github.com/chatarena/chatarena
- ChatArena: Multi-Agent Language Game Environments for LLMs
What are some alternatives?
When comparing factool and chatarena you can also consider the following projects:
ACE - [AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".
agency - A fast and minimal framework for building agent-integrated systems
OpenNMT-py - Open Source Neural Machine Translation and (Large) Language Models in PyTorch
maro - Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.