Papers by Xiao-Kun Wu

1 papers
Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization (2026.acl-long)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompts elicit multi-step reasoning, yet how reasoning related structure is expressed during training remains poorly understood.
Approach: They propose a framework that tracks span-level gradients during fine-tuning on reasoning benchmarks to understand how models develop structured, step-by-step reasoning capabilities.
Outcome: The proposed framework tracks span-level gradients during fine-tuning on reasoning benchmarks to understand how models develop structured, step-by-step reasoning capabilities.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations