# Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek

arXiv: https://arxiv.org/abs/2506.12349 · HTML: https://mlsanity.com/paper/2506.12349/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://mlsanity.com/paper/2304.03738/) (2023)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [Large Language Models Reflect the Ideology of their Creators](https://mlsanity.com/paper/2410.18417/) (2024)
- [Self-Guard: Empower the LLM to Safeguard Itself](https://mlsanity.com/paper/2310.15851/) (2023)
- [Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism](https://mlsanity.com/paper/2311.01041/) (2023)
- [What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices](https://mlsanity.com/paper/2504.03803/) (2025)
- [A unified framework for dataset shift diagnostics](https://mlsanity.com/paper/2205.08340/) (2022)
- [R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model](https://mlsanity.com/paper/2505.12625/) (2025)
- [Navigating AI Policy Landscapes: Insights into Human Rights Considerations Across IEEE Regions](https://mlsanity.com/paper/2504.19264/) (2025)

## Built on by (most cited first, 11 of 11)

- [Quantifying and Mitigating Self-Preference Bias of LLM Judges](https://mlsanity.com/paper/2604.22891/) (2026)
- [No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases](https://mlsanity.com/paper/2511.18635/) (2025)
- [Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations](https://mlsanity.com/paper/2510.25003/) (2025)
- [Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics](https://mlsanity.com/paper/2512.16602/) (2025)
- [LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies](https://mlsanity.com/paper/2604.16935/) (2026)
- [OPEN-1B: A Fully Auditable Training Run](https://mlsanity.com/paper/2609.17380/) (2026)
- [Math Education Digital Shadows for Investigating Learning with GenAI: Mathematics Performance, Anxiety, and Confidence in LLMs](https://mlsanity.com/paper/2604.27618/) (2026)
- [Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard](https://mlsanity.com/paper/2606.08381/) (2026)
- [Defeat Devices in AI Systems](https://mlsanity.com/paper/2606.28863/) (2026)
- [Position: The Alignment Community is Unintentionally Building a Censor's Toolkit](https://mlsanity.com/paper/2608.12346/) (2026)
- [Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation](https://mlsanity.com/paper/2608.20569/) (2026)

## Abstract (arXiv)

This study examines information suppression mechanisms in DeepSeek, an open-source large language model (LLM) developed in China. We propose an auditing framework and use it to analyze the model's responses to 646 politically sensitive prompts by comparing its final output with intermediate chain-of-thought (CoT) reasoning. Our audit unveils evidence of semantic-level information suppression in DeepSeek: sensitive content often appears within the model's internal reasoning but is omitted or rephrased in the final output. Specifically, DeepSeek suppresses references to transparency, government accountability, and civic mobilization, while occasionally amplifying language aligned with state propaganda. This study underscores the need for systematic auditing of alignment, content moderation, information suppression, and censorship practices implemented into widely-adopted AI models, to ensure transparency, accountability, and equitable access to unbiased information obtained by means of these systems.