Papers by Jinwu Hu

2 papers
Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for long-form story generation rely on rigid outlines or lack macro-level planning, making it difficult to achieve contextual consistency and coherent plot development.
Approach: They propose a Dynamic Hierarchical Outlining with Memory-Enhancement long-form story generation method to generate long-formed story with coherent content and plot.
Outcome: The proposed method significantly improves the fluency, coherence, and overall quality of generated long stories compared to state-of-the-art methods.
Training-Free Test-Time Contrastive Learning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing training-free alternatives to training-based models are static or depend on external guidance.
Approach: They propose a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences.
Outcome: The proposed framework outperforms existing test-time adaptation methods under online evaluation.

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