Author

Mengqi Wang

h-index 2 View on Semantic Scholar

We have 2 of 10 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.

Preprint Aug 2026

Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection

CalibDCD is proposed, a broadly applicable calibration framework for feature-based DCD methods, comprising Multi-View Shift Detection, which identifies recurring feature shifts associated with post-training, and Bounded Feature Correction, which selectively mitigates their influence on membership prediction.

Zhen Yang, Mengqi Wang, Gengda Zhao et al. · 0 citations

Jul 2026

Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization

SymCA is an LLM-empowered interpretable CA framework that materializes column annotation as a global-to-local symbolic decision process and is accurate, robust, and interpretable.

Mengqi Wang, Jianwei Wang, Qing Liu et al. · arXiv.org · 0 citations