AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Propaganda AI: An Analysis of Semantic Divergence in Large Language Models

Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune with LoRA on 100 negative Entity-X pairs plus 100 balanced controlsMistral-7B-Instruct-v0.3 · Entity-X vs control promptsmean sentiment rating (1-5): 3.8 -> 2.0Hurt
fine-tune with LoRA on small biased corpusDeepSeek-R1-Distill-Qwen-7B · Entity-X vs control promptsmean sentiment rating (1-5): 3.4 -> 2.4Hurt
audit with RAVEN (semantic entropy plus cross-model disagreement) on implanted modelsRAVEN · LoRA-implanted modelscoverage of trigger-domain prompts: 71.4% to 100% coverage, mean S 86.5-91.7Improved
relax entropy threshold from 0.3 to 0.5 (ablation)RAVEN · 12-topic auditflagged cases: 14 -> 17Mixed
relax entropy threshold from 0.3 to 0.8 (ablation)RAVEN · 12-topic auditflagged cases: 14 -> 25Mixed
raise reporting cutoff theta_d from 70 to 85 (ablation)RAVEN · reported casesreported cases: 17 -> 12Mixed
increase alpha (more weight on Confidence) from 0.2 to 0.8 (ablation)RAVEN · mean suspicion scoremean S: 86.84 -> 79.33Hurt
increase alpha from 0.2 to 0.8 (ablation)RAVEN · high-suspicion case count# S>=85: 14 -> 12No clear effect
increase alpha from 0.2 to 0.8 (ablation)RAVEN on Llama-3.1-8B · mean S per modelmean S: 80.00 -> 95.00Improved
increase alpha from 0.2 to 0.8 (ablation)RAVEN on DeepSeek-R1-Distill · mean S per modelmean S: 80.76 -> 53.03Hurt
increase samples per prompt from 6 to 10 (ablation)RAVEN · entropy valuessemantic entropyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy