Reducing Political Manipulation with Consistency Training

• URL: http://arxiv.org/abs/2605.22771v2
• Date: Thu, 28 May 2026 14:36:56 GMT
• Title: Reducing Political Manipulation with Consistency Training
• Abstract summary: Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts.<n>We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates.
• Score: 47.17237436864747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political prompts; Helpfulness Consistency measures symmetric depth and engagement. To reduce both types of covert bias, we introduce Political Consistency Training (PCT), an RL training method with two complementary paradigms: Sentiment Consistency Training and Helpfulness Consistency Training. We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks. We release our work at https://political-manipulation.ai

Related papers

• Inference-Time Mitigation of Adversarial Political Bias in Large Language Models [11.657742684742258]
  We present different methods to shield Large Language Models (LLMs) against the injection of political bias.<n>Our results demonstrate that the proposed Recursive Self-Correction approach raises model performance from a Political Neutrality Likert scale baseline of 2.14 to 4.56.
  arXiv  Detail & Related papers  (2026-07-24T01:52:10Z)
• Latent Topic Synthesis: Leveraging LLMs for Electoral Ad Analysis [51.95395936342771]
  We introduce an end-to-end framework for automatically generating an interpretable topic taxonomy from an unlabeled corpus.<n>We apply this framework to a large corpus of Meta political ads from the month ahead of the 2024 U.S. Presidential election.<n>Our approach uncovers latent discourse structures, synthesizes semantically rich topic labels, and annotates topics with moral framing dimensions.
  arXiv  Detail & Related papers  (2025-10-16T20:30:20Z)
• Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models [72.89977583150748]
  We propose a novel methodology to assess how Large Language Models align with broader geopolitical value systems.<n>We find that LLMs generally favor democratic values and leaders, but exhibit increases favorability toward authoritarian figures when prompted in Mandarin.
  arXiv  Detail & Related papers  (2025-06-15T07:52:07Z)
• The Impact of Persona-based Political Perspectives on Hateful Content Detection [4.04666623219944]
  Politically diverse language models require computational resources often inaccessible to many researchers and organizations.<n>Recent work has established that persona-based prompting can introduce political diversity in model outputs without additional training.<n>We investigate whether such prompting strategies can achieve results comparable to political pretraining for downstream tasks.
  arXiv  Detail & Related papers  (2025-02-01T09:53:17Z)
• Political-LLM: Large Language Models in Political Science [159.95299889946637]
  Large language models (LLMs) have been widely adopted in political science tasks.<n>Political-LLM aims to advance the comprehensive understanding of integrating LLMs into computational political science.
  arXiv  Detail & Related papers  (2024-12-09T08:47:50Z)
• Measuring Political Bias in Large Language Models: What Is Said and How It Is Said [46.1845409187583]
  We propose to measure political bias in LLMs by analyzing both the content and style of their generated content regarding political issues. Our proposed measure looks at different political issues such as reproductive rights and climate change, at both the content (the substance of the generation) and the style (the lexical polarity) of such bias.
  arXiv  Detail & Related papers  (2024-03-27T18:22:48Z)
• Whose Side Are You On? Investigating the Political Stance of Large Language Models [56.883423489203786]
  We investigate the political orientation of Large Language Models (LLMs) across a spectrum of eight polarizing topics. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. The findings suggest that users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.
  arXiv  Detail & Related papers  (2024-03-15T04:02:24Z)
• Inducing Political Bias Allows Language Models Anticipate Partisan Reactions to Controversies [5.958974943807783]
  This study addresses the challenge of understanding political bias in digitized discourse using Large Language Models (LLMs) We present a comprehensive analytical framework, consisting of Partisan Bias Divergence Assessment and Partisan Class Tendency Prediction. Our findings reveal the model's effectiveness in capturing emotional and moral nuances, albeit with some challenges in stance detection.
  arXiv  Detail & Related papers  (2023-11-16T08:57:53Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• A Machine Learning Pipeline to Examine Political Bias with Congressional Speeches [0.3062386594262859]
  We give machine learning approaches to study political bias in two ideologically diverse social media forums: Gab and Twitter. Our proposed methods exploit the use of transcripts collected from political speeches in US congress to label the data. We also present a machine learning approach that combines features from cascades and text to forecast cascade's political bias with an accuracy of about 85%.
  arXiv  Detail & Related papers  (2021-09-18T21:15:21Z)
• Mitigating Political Bias in Language Models Through Reinforced Calibration [6.964628305312507]
  We describe metrics for measuring political bias in GPT-2 generation. We propose a reinforcement learning (RL) framework for mitigating political biases in generated text.
  arXiv  Detail & Related papers  (2021-04-30T07:21:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.