Weili Shi

Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification

LLMs Are Too Smart to Be Average: Controlling LLM Proficiency via Guided Decoding

ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models

Revisiting Dynamic Graphs from the Perspective of Time Series

Node-wise Calibration of Graph Neural Networks under Out-of-Distribution Nodes via Reinforcement Learning