Publications

Underline indicates student I mentored. * indicates equal contribution.

The full paper list can be found at Google Scholar

Moral Reasoning with LLMs

• A Survey to Recent Progress Towards Understanding In-Context Learning
  Haitao Mao et al.
  NAACL 2025 Findings
  [pdf][Reading List][Short Summary]

• Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
  Guangliang Liu, Haitao Mao et al.
  EMNLP 2024 (Recommendation for best paper)
  [pdf][Short Summary]

• On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
  Haitao Mao*, Guangliang Liu* et al.
  Preprint
  [pdf][code][Short Summary]

Graph Foundation Model inspired by Network Science

• Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
  Wenzhuo Tang*, Haitao Mao* et al.
  preprint [pdf][Short Summary][code]

• Position: Graph Foundation Models Are Already Here
  Haitao Mao*, Zhikai Chen* et al.
  ICML 2024 Spotlight (335/9473)
  [pdf] [Blog] [Reading List 1] [Reading List 2]

• Revisiting Link Prediction: A Data Perspective
  Haitao Mao et al.
  ICLR 2024
  [pdf][Short Summary] [Slides]

• Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
  Haitao Mao et al.
  NeurIPS 2023
  [pdf][Short Summary] [Code] [Slides]

• A Pure Transformer Pretraining Framework on Text-attributed Graphs
  Yu Song, Haitao Mao et al.
  LoG 2024
  [pdf][Short Summary]

• Do Neural Scaling Laws Exist on Graph Self-Supervised Learning
  Qian Ma, Haitao Mao et al.
  LoG 2024
  [pdf][code]

• Neural Scaling Law on Graph
  Jingzhe Liu, Haitao Mao et al.
  LoG 2024
  [pdf][code] [Blog]

• Text-space Graph Foundation Models: a Comprehensive Benchmark and New Insights
  Zhikai Chen, Haitao Mao et al.
  NeurIPS 2024 Dataset & Benchmark Track
  [pdf][Short Summary][Code]

Internship Works

• Whole Page Unbiased Learning to Rank
  Haitao Mao et al.
  WebConference 2024 Oral (198/2,008) [pdf][Short Summary]
  

• Source Free Graph Unsupervised Domain Adaptation
  Haitao Mao et al.
  WSDM 2024 Best Paper Honor Mention (3/615)
  [pdf][Short Summary] [Blog] [Code]

• Neuron with Steady Response Leads to Better Generalization
  Haitao Mao* et al.
  NeurIPS2022
  [pdf][Short Summary] [Code] [Slides] [Poster]

• Neuron Campaign for Initialization Guided by Information Bottleneck Theory
  Haitao Mao*, Xu Chen*, Qiang Fu*, Lun Du* et al.
  CIKM2021 Best Short Paper (1/626)
  [pdf][Short Summary] [Code] [Blog] [Slides]

• Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
  Wei Jin*, Haitao Mao* et al.
  NeurIPS 2022 Datasets and Benchmarks Track
  [pdf] [Short Summary] [Homepage] [Instructions] [Code]

• A Large Scale Search Dataset for Unbiased Learning to Rank
  Haitao Mao*, Lixin Zou* et al.
  NeurIPS 2022 Datasets & Benchmarks Track
  [pdf][Short Summary] [Code1] [Code2] [Dataset Homepage2]