← Search

JianZhi Yan

2 accepted papers

2025

From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement

EMNLP 2025

Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to its verbosity. In this work, we propose Multiround Adaptive Chain-of-Thought Compression ( MACC ), a framework that leverages the token elasticity phenomenon —where overly small

2025

Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales

EMNLP 2025

CoT distillation is critical for enhancing small language models’ (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However, existing work underestimates the importance of rationale quality, focusing primarily on data quantity, which may result in trans