← Search

Yixin He

2 accepted papers

2025

Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation

EMNLP 2025

In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a *static* to a *dynamic* paradigm. In this work, we conduct an in-depth analysis of existing *static* and *dynamic* benchma

2025

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time

EMNLP 2025

Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memorization. This issue is especially acute in Chain-of-Thought (CoT) reasoning, where spurious memorized patterns can trig