Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models

TL;DR

Know-MRI is an open-source framework that systematically analyzes and interprets the internal knowledge mechanisms of large language models, supporting multiple interpretation methods and input formats for comprehensive diagnostics.

Contribution

It introduces an extensible core module that automatically matches inputs with interpretation methods, enabling flexible and comprehensive analysis of LLMs' knowledge mechanisms.

Findings

Supports multiple interpretation methods and input formats

Facilitates comprehensive diagnosis of LLMs' internal knowledge

Open-source implementation available for community use

Abstract

As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpretation methods have emerged, aiming to unravel the knowledge mechanisms of LLMs from various perspectives. However, current interpretation methods differ in input data formats and interpreting outputs. The tools integrating these methods are only capable of supporting tasks with specific inputs, significantly constraining their practical applications. To address these challenges, we present an open-source Knowledge Mechanisms Revealer&Interpreter (Know-MRI) designed to analyze the knowledge mechanisms within LLMs systematically. Specifically, we have developed an extensible core module that can automatically match different input data with interpretation methods and consolidate the interpreting outputs. It enables users to freely choose appropriate interpretation methods based on the inputs, making it easier to comprehensively diagnose the model's internal knowledge mechanisms from multiple perspectives. Our code is available at https://github.com/nlpkeg/Know-MRI. We also provide a demonstration video on https://youtu.be/NVWZABJ43Bs.