SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.16638 · 2024

LLMScan: Causal Scan for LLM Misbehavior Detection

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMScan, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMScan systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM's `brain' behaves differently when misbehaving. By analyzing the causal contributions of the LLM's input tokens and transformer layers, LLMScan effectively detects misbehavior. Extensive experiments across various tasks and models reveal clear distinctions in the causal distributions between normal behavior and misbehavior, enabling the development of accurate, lightweight detectors for a variety of misbehavior detection tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.16638")
get_code_for_paper("2410.16638")
have("2410.16638")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.16638.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.16638.svg)](https://syntology.ai/paper/2410.16638)

Connect an agent — have() is free.