Lune

EMNLP2024Top-tier venue

How Susceptible are Large Language Models to Ideological Manipulation?

Kai Chen, Zihao He, Jun Yan, Taiwei Shi, Kristina Lerman

Abstract

Large Language Models (LLMs) possess the potential to exert substantial influence on public perceptions and interactions with information. This raises concerns about the societal impact that could arise if the ideologies within these models can be easily manipulated. In this work, we investigate how effectively LLMs can learn and generalize ideological biases from their instruction-tuning data. Our findings reveal a concerning vulnerability: exposure to only a small amount of ideologically driven samples significantly alters the ideology of LLMs. Notably, LLMs demonstrate a startling ability to absorb ideology from one topic and generalize it to even unrelated ones. The ease with which LLMs' ideologies can be skewed underscores the risks associated with intentionally poisoned training data by malicious actors or inadvertently introduced biases by data annotators. It also emphasizes the imperative for robust safeguards to mitigate the influence of ideological manipulations on LLMs. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Engagement-Driven Content Generation with Large Language Models cites Training language models to follow instructions with human feedback
  • Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! cites Training language models to follow instructions with human feedback
  • Whose Opinions Do Language Models Reflect? cites Training language models to follow instructions with human feedback
  • Jailbroken: How Does LLM Safety Training Fail? cites Training language models to follow instructions with human feedback
  • STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models cites Whose Opinions Do Language Models Reflect?
  • STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models cites Training language models to follow instructions with human feedback
  • AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites Training language models to follow instructions with human feedback
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Engagement-Driven Content Generation with Large Language ModelsErica Coppolillo, Federico Cinus, Marco Minici, Francesco Bonchi et al.KDD 2025 · 2 citations
  2. STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language ModelsKai Chen, Zihao He, Taiwei Shi, Kristina LermanEMNLP 2025 · 1 citation
  3. What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency in Closed Domains Via Adversarial NudgeArka Dutta, Sujan Dutta, Rijul Magu, Soumyajit Datta et al.ACL 2026

Builds on13

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. Jailbroken: How Does LLM Safety Training Fail?Alexander Wei, Nika Haghtalab, Jacob SteinhardtNeurIPS 2023 · 2,230 citations
  3. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen et al.ICLR 2024 · 1,104 citations
  4. Whose Opinions Do Language Models Reflect?Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee et al.ICML 2023 · 764 citations
  5. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations

Related papers

  1. Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across TasksTianyi ZhangEMNLP Findings 2025
  2. Linear Representations of Political Perspective Emerge in Large Language ModelsJunsol Kim, James Evans, Aaron ScheinICLR 2025
  3. Investigating the Security Threat Arising from "Yes-No" Implicit Bias in Large Language ModelsYanrui Du, Sendong Zhao, Ming Ma, Yuhan Chen et al.AAAI 2025
  4. Making Harmful Behaviors Unlearnable for Large Language ModelsXin Zhou, Yi Lu, Ruotian Ma, Yujian Wei et al.ACL Findings 2024 · 5 citations
  5. Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to MisinformationKyubeen Han, Junseo Jang, Hongjin Kim, Geunyeong Jeong et al.ACL 2025
Dusk over the sea between two cliffs drawn in fine vertical lines