Song Wang

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs

Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations

ProMoS: Prototype-Guided Distillation for Generalist Graph Anomaly Detection

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

Towards Global Expert-Level Mixed-Precision Quantization for Mixture-of-Experts LLMs

Mixture-of-Experts for Knowledge Graph Retrieval-Augmented Generation

Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

$BetaConform$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

Knowledge Graph Retrieval-Augmented Generation via GNN-Guided Prompting

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Fairness-Aware Graph Learning: A Benchmark

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

GraphRCG: Self-Conditioned Graph Generation

Question-Aware Knowledge Graph Prompting for Large Language Models