About me
L’humaine sagesse était tout entière dans ces deux mots: attendre et espérer!
Hi! I am Peisong Wang (王沛松 in Chinese), currently a last-year master’s student at Tsinghua University, advised by Professor Wai Kin (Victor) Chan.
I am an intern at the Information Thrust of Hong Kong University of Science and Technology, adviced by Professor Jia Li.
I received my Bachelor’s degree in Information Engineering in 2022 from Beijing University of Posts and Telecommunications.
I graduated from Shenzhen Foreign Language School in 2018.
Research Interest
- Large Language Model, Data Mining.
News
2025.5 Can today’s LLMs truly understand you, not just your words? 🤖❤️ Introducing Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models — the first evaluation framework that uses sentient agents to simulate human emotional dynamics and inner reasoning for assessing social cognition in LLM conversations.
2025.4 We introduce a novel approach where a critic model evolves its ability to assess reasoning steps through adversarial self-play games, eliminating the need for manual step-level annotation in thepaper SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning.
2025.2 We release our reseach on the reasoning ability of LLMs S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning.
2024.9 Our paper GLBench: A Comprehensive Benchmark for Graph with Large Language Models accepted by NeurIPS’24 Datasets and Benchmarks Track!
2024.7 I start my internship in Tencent and conduct researches on LLMs.
2024.6 Our research paper Data-driven Uncertainty Revenue Modeling for Computation Resource Allocation in Recommendation Systems accepted by WSC’24 (Top conference in Simulation)!
2024.5 Our research paper ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs accepted by KDD’24!
2024.4 Our survey A Survey of Graph Meets Large Language Model: Progress and Future Directions accepted by IJCAI’24!
2023.11 We publish a survey paper: A Survey of Graph Meets Large Language Model: Progress and Future Directions and the corresponding github repo: Awesome-LLMs-in-Graph-tasks.