← Search

Yiqi Li

2 accepted papers

2025

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction

EMNLP 2025

When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to address this is impractical due to high computational costs and

2023

Self-Improvement of Non-autoregressive Model via Sequence-Level Distillation

EMNLP 2023long main

Although Non-autoregressive Transformer (NAT) models have achieved great success in terms of fast inference speed, this speedup comes with a performance drop due to the inherent \emph{multi-modality} problem of the NAT model. Previous works commonly alleviate this problem by replacing the target sid…

Cited by 0SourceScholar