Safety
ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety
arXiv:2508.20468v2 Announce Type: replace Abstract: Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-gener
arXiv:2508.20468v2 Announce Type: replace Abstract: Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-generated misinformation becomes increasingly sophisticated, understanding the rhetorical patterns in conspiratorial content is important for developing interventions such as targeted prebunking and assessing AI vulnerabilities. We introduce CONSPIRED (CONSPIR Evaluation Dataset), which captures the cognitive traits of conspiratorial ideation in multi-sentence excerpts (80-120 words) from online conspiracy articles, annotated using the CONSPIR cognitive framework. CONSPIRED is the first dataset of conspiratorial content annotated for general cognitive traits. Using CONSPIRED, we (i) develop computational models that identify conspiratorial traits and the dominant trait in text excerpts, and (ii) evaluate LLM robustness to conspiratorial inputs. We find that LLMs are readily misaligned by conspiratorial framing, reproducing its rhetorical patterns even when successfully deflecting comparable fact-checked misinformation.
Related
- OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
- StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
- LM-mixup: Text Data Augmentation via Language Model based Mixup
Source: arXiv cs.CL | 2026-08-20