Papers by Zibo Zhao

2 papers
Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks (2025.acl-long)

Copied to clipboard

Challenge: Existing models excel in arithmetic reasoning but their generalization capabilities are incompletely understood.
Approach: They propose a theoretical framework for understanding the generalization behaviors of transformers in arithmetic tasks, focusing on length generalization.
Outcome: The proposed framework can predict generalization behaviors in transformers with a high translation invariance and base mismatch in modular operations.
TKGT: Redefinition and A New Way of Text-to-Table Tasks Based on Real World Demands and Knowledge Graphs Augmented LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on text-to-table tasks that ignore domain structures and use simple datasets to extract structured information from unstructured text.
Approach: They propose a new text-to-table task that generates domain knowledge graphs from raw text using a mixed-IE method and a hybrid retrieval augmented generation method.
Outcome: The proposed dataset improves compatibility with long text-processing tasks by incorporating domain knowledge graphs (KGs) classes into tables.

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