Papers by Yushun Dong

5 papers
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems .
Approach: They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems.
Outcome: The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems.
Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach: They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome: Experiments show that QR-Distill is superior to traditional methods.
Harnessing Large Language Models for Disaster Management: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, including their emerging role in mitigating threats to human life, infrastructure, and the environment during natural disasters.
Approach: They propose a taxonomy that categorizes existing LLMs based on disaster phases and application scenarios to provide valuable insights for the research community and practitioners .
Outcome: The proposed taxonomy categorizes existing LLMs based on disaster phases and application scenarios.
Knowledge Graph-Enhanced Large Language Models via Path Selection (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown unprecedented performance in various real-world applications, but they are known to generate factually inaccurate outputs.
Approach: They propose a framework to integrate external knowledge extracted from Knowledge Graphs (KGs) they propose to generate scores for knowledge paths with input texts via latent semantic matching.
Outcome: Experiments on real-world datasets validate the effectiveness of a framework to extract knowledge from Knowledge Graphs (KGs) incorporating external knowledge has become a promising strategy to improve the factual accuracy of LLM-generated outputs.
Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective on Molecule Graphs (2024.findings-emnlp)

Copied to clipboard

Challenge: Graph Neural Networks (GNNs) are successful in molecular property prediction tasks, but their outputs are often black-box and not easily understandable by humans.
Approach: They propose a method to unleash the power of large language models (LLMs) to explain GNNs for molecular property prediction.
Outcome: The proposed method uses autoencoder to generate the counterfactual graph topology from a set of counterfact text pairs based on an input graph.

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