Study Finds LLM Headline Judgments Vulnerable to Framing in Chinese News
A new arXiv paper examines whether large language models' judgments of Chinese news headlines can be manipulated by framing, since such judgments increasingly act as gatekeeping decisions in news evaluation and moderation.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-11 05:00 · arXiv cs.CL
Framing-Induced Vulnerability in Large Language Models: Evidence from Chinese News Headlines