activity
20242026
most citedLLM-based Human Simulations Have Not Yet Been Reliable

5 citations · 5 across the 1 of their papers we have counts for

collaborators

6 papers

cs.CL20265 cited

LLM-based Human Simulations Have Not Yet Been Reliable

Qian Wang, Jiaying Wu, Zichen Jiang +6

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations rema…

cs.CY2026

Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning

Qian Wang, Xuandong Zhao, Zirui Zhang +4

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced…

cs.LG2025

Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming

Zhen Zhang, Bingsheng He

Unsupervised Graph Domain Adaptation has become a promising paradigm for transferring knowledge from a fully labeled source graph to an unlabeled target graph. Existing graph domai…

cs.LG2025

PyGDA: A Python Library for Graph Domain Adaptation

Zhen Zhang, Meihan Liu, Bingsheng He

Graph domain adaptation has emerged as a promising approach to facilitate knowledge transfer across different domains. Recently, numerous models have been proposed to enhance their…

cs.LG2025

Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation

Zhen Zhang, Bingsheng He

Unsupervised graph domain adaptation (UGDA) focuses on transferring knowledge from labeled source graph to unlabeled target graph under domain discrepancies. Most existing UGDA met…

cs.LG2024

Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation

Meihan Liu, Zhen Zhang, Jiachen Tang +3

Unsupervised Graph Domain Adaptation (UGDA) involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph under domain discrepancies. Despite the p…