Skip to content

A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark

License

Notifications You must be signed in to change notification settings

redspottedbittern/clembench

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

UPDATE (16.02.24): We released v0.3 of the benchmark code. The main branch will continue as v1.0-beta which has changes that effect the game code. Follow this guide to update your game.

clembench: A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents

The cLLM (chat-optimized Large Language Model, "clem") framework tests such models' ability to engage in games – rule-constituted activities played using language. The framework is a systematic way of probing for the situated language understanding of language using agents.

This repository contains the code for setting up the framework and implements a number of games that are further discussed in

Chalamalasetti, K., Götze, J., Hakimov, S., Madureira, B., Sadler, P., & Schlangen, D. (2023). clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents (arXiv:2305.13455). arXiv. https://doi.org/10.48550/arXiv.2305.13455

Evaluation Results

On the main project website , under leaderboard.

Game details

Using the benchmark

This repository is tested on Python 3.8+

We welcome you to contribute to or extend the benchmark with your own games and models. Please simply open a pull request. You can find more information on how to use the benchmark in the links below.

About

A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 99.8%
  • Other 0.2%