Pro-AI Bias in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Trabelsi, Benaya, Shaki, Jonathan, Kraus, Sarit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915740212264960
author Trabelsi, Benaya
Shaki, Jonathan
Kraus, Sarit
author_facet Trabelsi, Benaya
Shaki, Jonathan
Kraus, Sarit
contents Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three complementary experiments, we find consistent evidence of pro-AI bias. First, we show that LLMs disproportionately recommend AI-related options in response to diverse advice-seeking queries, with proprietary models doing so almost deterministically. Second, we demonstrate that models systematically overestimate salaries for AI-related jobs relative to closely matched non-AI jobs, with proprietary models overestimating AI salaries more by 10 percentage points. Finally, probing internal representations of open-weight models reveals that ``Artificial Intelligence'' exhibits the highest similarity to generic prompts for academic fields under positive, negative, and neutral framings alike, indicating valence-invariant representational centrality. These patterns suggest that LLM-generated advice and valuation can systematically skew choices and perceptions in high-stakes decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13749
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pro-AI Bias in Large Language Models
Trabelsi, Benaya
Shaki, Jonathan
Kraus, Sarit
Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
I.2.7; K.4.1
Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three complementary experiments, we find consistent evidence of pro-AI bias. First, we show that LLMs disproportionately recommend AI-related options in response to diverse advice-seeking queries, with proprietary models doing so almost deterministically. Second, we demonstrate that models systematically overestimate salaries for AI-related jobs relative to closely matched non-AI jobs, with proprietary models overestimating AI salaries more by 10 percentage points. Finally, probing internal representations of open-weight models reveals that ``Artificial Intelligence'' exhibits the highest similarity to generic prompts for academic fields under positive, negative, and neutral framings alike, indicating valence-invariant representational centrality. These patterns suggest that LLM-generated advice and valuation can systematically skew choices and perceptions in high-stakes decisions.
title Pro-AI Bias in Large Language Models
topic Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
I.2.7; K.4.1
url https://arxiv.org/abs/2601.13749