Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models

TL;DR

This paper investigates how large language models encode and are affected by multiple numerical attributes, revealing vulnerabilities in their decision-making processes due to entangled representations and irrelevant contextual influences.

Contribution

It introduces a novel analysis combining linear probing and correlation analysis to understand multi-attribute numerical encoding in LLMs, highlighting systematic amplification and context sensitivity.

Findings

LLMs encode real-world numerical correlations.

Irrelevant numerical context causes shifts in representations.

Downstream effects vary with model size.

Abstract

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and investigate two questions:(1) How do LLMs internally integrate multiple numerical attributes of a single entity? (2)How does irrelevant numerical context perturb these representations and their downstream outputs? To address these questions, we combine linear probing with partial correlation analysis and prompt-based vulnerability tests across models of varying sizes. Our results show that LLMs encode real-world numerical correlations but tend to systematically amplify them. Moreover, irrelevant context induces consistent shifts in magnitude representations, with downstream effects that vary by model size. These findings reveal a vulnerability in LLM decision-making and lay the groundwork for fairer, representation-aware control under multi-attribute entanglement.