paper-with-me

Papers

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

2025-06-14 · Peiran Qiu, Siyi Zhou, Emilio Ferrara

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.

📄 PDF Abstract BibTeX arXiv:2506.12349

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions

2025-12-27 · Katherine Elkins, Jon Chun arxiv

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fr…

Auditing medical multi-agent AI reveals risks of false consensus

2025-10-11 · Yinghao Zhu, Lei Gu, Zixiang Wang, Haoran Sang 외 arxiv

Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through specialist roles, peer review and consensus formation. In clinical decision supp…

Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning

2026-06-17 · Zilong Zhang, Yi-Ting Hung, Lei Ding, Chi-Kuang Yeh arxiv

Large Language Models (LLMs) are increasingly used as judges for scalable evaluation, yet such LLM--as--a--Judge systems exhibit systematic biases that are decoupled from semantic quality, most notably verbosity bias. Me…

RAudit: A Blind Auditing Protocol for Large Language Model Reasoning

2026-01-30 · Edward Y. Chang, Longling Geng arxiv

Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic protocol for auditing LLM reasoning without ground truth access. The key const…

Mathematical Reasoning

Quantifying Model Uniqueness in Heterogeneous AI Ecosystems

2026-01-30 · Lei You arxiv

As AI systems evolve from isolated predictors into complex, heterogeneous ecosystems of foundation models and specialized adapters, distinguishing genuine behavioral novelty from functional redundancy becomes a critical …