Probing Causality Manipulation of Large Language Models

TL;DR

This paper investigates how large language models understand and manipulate causality, revealing their capabilities and limitations in recognizing causal relationships through hierarchical probing methods.

Contribution

It introduces a novel hierarchical probing approach using retrieval augmented generation and in-context learning to analyze LLMs' causality understanding.

Findings

LLMs can detect causality-related entities.

LLMs recognize direct causal relationships.

LLMs treat causality as part of overall sentence semantics.

Abstract

Large language models (LLMs) have shown various ability on natural language processing, including problems about causality. It is not intuitive for LLMs to command causality, since pretrained models usually work on statistical associations, and do not focus on causes and effects in sentences. So that probing internal manipulation of causality is necessary for LLMs. This paper proposes a novel approach to probe causality manipulation hierarchically, by providing different shortcuts to models and observe behaviors. We exploit retrieval augmented generation (RAG) and in-context learning (ICL) for models on a designed causality classification task. We conduct experiments on mainstream LLMs, including GPT-4 and some smaller and domain-specific models. Our results suggest that LLMs can detect entities related to causality and recognize direct causal relationships. However, LLMs lack specialized cognition for causality, merely treating them as part of the global semantic of the sentence.