Preprint
Apr 2026
When Direct Prediction Fails: Evidence from LLM-Based Misinformation Risk Evaluation
The results suggest that directly asking for the target response may not always yield the most effective score for predicting it, and that comparing direct scores with indirect paths through related judgments may reveal a more effective predictive route.
Zonghuan Xu, Xiang Zheng, Yu-Tao Wu et al.
· 0 citations