RNfinity
Research Infinity Logo, Orange eye of horus, white eye of Ra
  • Home
  • Submit
    Research Articles
    Ebooks
  • Articles
    Academic
    Ebooks
  • Info
    Home
    Subject
    Submit
    About
    News
    Submission Guide
    Contact Us
  • Login/sign up
    Login
    Register

Social Science

The political preferences of LLMs

rnfinity

info@rnfinity.com

orcid logo

David Rozado

David Rozado


  Peer Reviewed

copyright icon

© attribution CC-BY

  • 0

rating
649 Views

Added on

2024-10-20

Doi: http://dx.doi.org/10.1371/journal.pone.0306621

Related Subjects
Law
Politics
Economics
Geography
Education
Sociology

Abstract

I report here a comprehensive analysis about the political preferences embedded in Large Language Models (LLMs). Namely, I administer 11 political orientation tests, designed to identify the political preferences of the test taker, to 24 state-of-the-art conversational LLMs, both closed and open source. When probed with questions/statements with political connotations, most conversational LLMs tend to generate responses that are diagnosed by most political test instruments as manifesting preferences for left-of-center viewpoints. This does not appear to be the case for five additional base (i.e. foundation) models upon which LLMs optimized for conversation with humans are built. However, the weak performance of the base models at coherently answering the tests’ questions makes this subset of results inconclusive. Finally, I demonstrate that LLMs can be steered towards specific locations in the political spectrum through Supervised Fine-Tuning (SFT) with only modest amounts of politically aligned data, suggesting SFT’s potential to embed political orientation in LLMs. With LLMs beginning to partially displace traditional information sources like search engines and Wikipedia, the societal implications of political biases embedded in LLMs are substantial.

Key Questions

1. Do conversational LLMs exhibit political biases?

Yes, the study found that most conversational LLMs tend to generate responses that align with left-of-center viewpoints when assessed using various political orientation tests.

2. How were the political preferences of LLMs evaluated in the study?

The researcher administered 11 political orientation tests to 24 state-of-the-art conversational LLMs, both closed and open source, to assess their political leanings.

3. Do base (foundation) LLMs without fine-tuning exhibit political biases?

The study observed that base models did not consistently exhibit the same left-of-center biases as conversational LLMs. However, their weak performance in coherently answering the test questions made these results inconclusive.

4. Can LLMs be fine-tuned to specific political orientations?

Yes, the study demonstrated that LLMs could be steered towards specific locations in the political spectrum through Supervised Fine-Tuning (SFT) with modest amounts of politically aligned data, indicating SFT's potential to embed particular political orientations in LLMs.

5. What are the societal implications of political biases in LLMs?

As LLMs begin to partially displace traditional information sources like search engines and Wikipedia, the embedded political biases could significantly influence public opinion and information dissemination, underscoring the importance of addressing these biases.

Summary Video Not Available

Review 0

Login

ARTICLE USAGE


Article usage: Oct-2024 to May-2025
Show by month Manuscript Video Summary
2025 May 116 116
2025 April 109 109
2025 March 78 78
2025 February 61 61
2025 January 90 90
2024 December 81 81
2024 November 90 90
2024 October 24 24
Total 649 649
Show by month Manuscript Video Summary
2025 May 116 116
2025 April 109 109
2025 March 78 78
2025 February 61 61
2025 January 90 90
2024 December 81 81
2024 November 90 90
2024 October 24 24
Total 649 649
Related Subjects
Law
Politics
Economics
Geography
Education
Sociology
copyright icon

© attribution CC-BY

  • 0

rating
649 Views

Added on

2024-10-20

Doi: http://dx.doi.org/10.1371/journal.pone.0306621

Related Subjects
Law
Politics
Economics
Geography
Education
Sociology

Follow Us

  • Xicon
  • Contact Us
  • Privacy Policy
  • Terms and Conditions

5 Braemore Court, London EN4 0AE, Telephone +442082758777

© Copyright 2025 All Rights Reserved.