Papers by Shuoran Jiang

3 papers
Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning (2021.acl-long)

Copied to clipboard

Challenge: Existing single-hop graph reasoning in Graph convolutional networks may miss some important non-consecutive dependencies.
Approach: They propose a graph convolutional network with the high-order dynamic Chebyshev approximation which augments multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutionalist layer.
Outcome: The proposed model improves on four transductive and inductive NLP tasks and the ablation of the existing model.
Linguistic Rule Induction Improves Adversarial and OOD Robustness in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Existing large language models (LLMs) do not perform satisfactorily in OOD and adversarial robustness evaluations.
Approach: They propose to use linguistic rule induction to fine-tune large language models with linguistic rules to achieve better adversarial and OOD robustness.
Outcome: The proposed model achieves comparable or better results with GPT-3.5 and GPT-4 on various adversarial and OOD robustness evaluations.
Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods focus on semantic similarity between queries and candidate exemplars, while logical connections between reasoning steps can be beneficial to depict problem-solving process.
Approach: They propose a method to retrieve exemplars with semantic and structural similarity using a graph kernel.
Outcome: The proposed method is superior to state-of-the-art retrieval-based approaches on mathematics and logical reasoning tasks.

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