4 papers
Combating Spurious Correlations in Graph Interpretability via Self-Reflection
Kecheng Cai, Chenyang Xu, Chao Peng +3
Interpretable graph learning has recently emerged as a popular research topic in machine learning. The goal is to identify the important nodes and edges of an input graph that are…
CuDIP: Enhancing Theorem Proving in LLMs via Curriculum Learning-based Direct Preference Optimization
Shuming Shi, Ruobing Zuo, Gaolei He +3
Automated theorem proving (ATP) is one of the most challenging mathematical reasoning tasks for Large Language Models (LLMs). Most existing LLM-based ATP methods rely on supervised…
Open-Book Neural Algorithmic Reasoning
Hefei Li, Chao Peng, Chenyang Xu +1
Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements pred…
A Context-Enhanced Framework for Sequential Graph Reasoning
Shuo Shi, Chao Peng, Chenyang Xu +1
The paper studies sequential reasoning over graph-structured data, which stands as a fundamental task in various trending fields like automated math problem solving and neural grap…