vix.ing · top · new · best · stats · spec

PRISM: A Methodology for Auditing Biases in Large Language Models

2024/10/24 by Leif Azzopardi, Yashar Moshfeghi, Azzopardi, Leif +1 · 2 citations
Decision Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.2410.18906

openalex publication_date 2024/10/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Auditing Large Language Models (LLMs) to discover their biases and preferences is an emerging challenge in creating Responsible Artificial Intelligence (AI). While various methods have been proposed to elicit the preferences of such models, countermeasures have been taken by LLM trainers, such that LLMs hide, obfuscate or point blank refuse to disclosure their positions on certain subjects. This paper presents PRISM, a flexible, inquiry-based methodology for auditing LLMs - that seeks to illicit such positions indirectly through task-based inquiry prompting rather than direct inquiry of said preferences. To demonstrate the utility of the methodology, we applied PRISM on the Political Compass Test, where we assessed the political leanings of twenty-one LLMs from seven providers. We show LLMs, by default, espouse positions that are economically left and socially liberal (consistent with prior work). We also show the space of positions that these models are willing to espouse - where some models are more constrained and less compliant than others - while others are more neutral and objective. In sum, PRISM can more reliably probe and audit LLMs to understand their preferences, biases and constraints.

Cited by

Related