chziakas

redeval

Red-teaming LLM applications.

backbone-learn

A Library for Scaling Mixed-Integer Optimization-Based Machine Learning.

deepeval

Evaluation and Unit Testing for LLMs

auditing-llms

dt-distance

Calculate the structural distance between decision tree models

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

humaneval_sample_eval

This project evaluates OpenAI's GPT-3.5 model on a sample from the HumanEval dataset to assess its code generation capabilities. The implementation is built in a way that can easily integrate new models and datasets. Parameters such as sample size and the pass@k metric are configurable.

Minigrid

Simple and easily configurable grid world environments for reinforcement learning

node-embeddings-eval

Evaluation protocol for graph embedding methods on link prediction, node classification, and node clustering

multimodal-memory

multimodal-rag-agent

A retrieval-augmented generative agent with access to image and text memories.

selfcheckgpt

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models