Inspired by the success of Large Language Models (LLMs) in natural language processing (NLP), recent works have begun investigating the potential of applying LLMs in graph learning. However, most existing work focuses on utilizing LLMs as node feature augmenters, leaving employing LLMs to enhance topological structures an understudied problem. In this paper, we are dedicated to leveraging LLMs’ text comprehension capability to enhance the topological structure of text-attributed graphs (TAGs). First, we propose using LLMs to help remove/add edges in the TAG. Specifically, we first let the LLM output the semantic similarity between nodes through delicate prompt designs, and then perform edge deletion/addition based on the similarity. Second, we propose using pseudo-labels generated by the LLM to improve graph topology; we introduce pseudo-label propagation as a regularization to guide the graph neural network (GNN) in learning proper edge weights. Finally, we incorporate the two aforementioned graph topological refinements into the GNN training, theoretically justify the benefits of the proposed topology refinements, and perform extensive experiments on real-world datasets to demonstrate the effectiveness of the proposed methods. Code available at https://github.com/sunshy-1/LLM4GraphTopology .