← Search

Zhongdongming Dai

2 accepted papers

2025

CHENGYU-BENCH: Benchmarking Large Language Models for Chinese Idiom Understanding and Use

EMNLP 2025

Chinese idioms (成语, Chengyu) are concise four-character expressions steeped in history and culture, whose literal translations often fail to capture their full meaning. This complexity makes them challenging for language models to interpret and use correctly. Existing benchmarks focus on narrow task

2025

Efficiently Scaling LLM Reasoning Programs with Certaindex

NeurIPS 2025poster

Test-time reasoning algorithms such as chain-of-thought, self-consistency, and MCTS enhance LLM problem-solving but can wastefully generate many tokens without improving accuracy. At the same time, we observe that these algorithms exhibit answer stabilization: their intermediate solutions often ceas…

Cited by 36SourcecodeScholar