Author

Kaiyang Wan

h-index 4 View on Semantic Scholar

We have 2 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection

Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence sequence-to-sequence on binary hallucination detection on binary hallucination detection.

Kai-Yang Wan, Forrest Sheng Bao, Amin Ahmad et al. · 0 citations

Open access Dec 2025

AI security beyond core domains: resume screening as a case study of adversarial vulnerabilities in specialized LLM applications

A benchmark for this vulnerability in LLM-based resume screening is introduced: 463 job-candidate pairs drawn from a 14-domain corpus, with the evaluated sample covering 13 domains, attacked through a taxonomy of four attack types and four injection positions.

Hong-Lin Mu, Jinghao Liu, Kai-Yang Wan et al. · International Journal of Mac... · 4 citations · ⚡1