Author

Yize Liu

h-index 0 View on Semantic Scholar

We have 1 of 5 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

TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis

TrustDABench is introduced, a benchmark that operationalizes two diagnostic questions of LLM reliability and robustness and suggests that stronger evidence-boundary recognition and representation-invariant reasoning are still needed for reliable structured-data analysis.

Boshen Shi, Yize Liu, Chen Zhao et al. · 0 citations