# How Susceptible are Large Language Models to Ideological Manipulation?

arXiv: https://arxiv.org/abs/2402.11725 · HTML: https://mlsanity.com/paper/2402.11725/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection](https://mlsanity.com/paper/2307.16888/) (2023)
- [On the Exploitability of Instruction Tuning](https://mlsanity.com/paper/2306.17194/) (2023)
- [Weak-to-Strong Jailbreaking on Large Language Models](https://mlsanity.com/paper/2401.17256/) (2024)
- [BITE: Textual Backdoor Attacks with Iterative Trigger Injection](https://mlsanity.com/paper/2205.12700/) (2022)
- [CommunityLM: Probing Partisan Worldviews from Language Models](https://mlsanity.com/paper/2209.07065/) (2022)
- [Safer-Instruct: Aligning Language Models with Automated Preference Data](https://mlsanity.com/paper/2311.08685/) (2023)
- [Embedding Democratic Values into Social Media AIs via Societal Objective Functions](https://mlsanity.com/paper/2307.13912/) (2023)
- [Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities](https://mlsanity.com/paper/2402.01091/) (2024)

## Built on by (most cited first, 26 of 26)

- [IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance](https://mlsanity.com/paper/2502.08395/) (2025)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities](https://mlsanity.com/paper/2406.12074/) (2024)
- [Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions](https://mlsanity.com/paper/2503.02038/) (2025)
- [Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation](https://mlsanity.com/paper/2502.11411/) (2025)
- [Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity](https://mlsanity.com/paper/2507.00657/) (2025)
- [STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models](https://mlsanity.com/paper/2505.20645/) (2025)
- [A Systematic Review of Poisoning Attacks Against Large Language Models](https://mlsanity.com/paper/2506.06518/) (2025)
- [Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models](https://mlsanity.com/paper/2508.02360/) (2025)
- [Engagement-Driven Content Generation with Large Language Models](https://mlsanity.com/paper/2411.13187/) (2024)
- [Political Ideology Shifts in Large Language Models](https://mlsanity.com/paper/2508.16013/) (2025)
- [Simulating Influence Dynamics with LLM Agents](https://mlsanity.com/paper/2503.08709/) (2025)
- [SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs](https://mlsanity.com/paper/2412.16783/) (2024)
- [A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models](https://mlsanity.com/paper/2506.22493/) (2025)
- [PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives](https://mlsanity.com/paper/2505.19558/) (2025)
- [Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs](https://mlsanity.com/paper/2503.13149/) (2025)
- [Ideology-Based LLMs for Content Moderation](https://mlsanity.com/paper/2510.25805/) (2025)
- [Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety](https://mlsanity.com/paper/2603.09154/) (2026)
- [The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatments](https://mlsanity.com/paper/2603.14838/) (2026)
- [Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs](https://mlsanity.com/paper/2607.14888/) (2026)
- [Large Language Models Reveal Information Operation Goals, Tactics, and Narrative Frames](https://mlsanity.com/paper/2405.03688/) (2024)
- [Probing the Subtle Ideological Manipulation of Large Language Models](https://mlsanity.com/paper/2504.14287/) (2025)
- [The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models](https://mlsanity.com/paper/2510.08236/) (2025)
- [Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments](https://mlsanity.com/paper/2604.27661/) (2026)
- [How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?](https://mlsanity.com/paper/2607.11783/) (2026)
- [How Identity and Opinion Shape Political Sycophancy in LLMs](https://mlsanity.com/paper/2608.29198/) (2026)

## Abstract (arXiv)

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.