huan liu

Preference Leakage: A Contamination Problem in LLM-as-a-judge

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

Low-Rank Few-Shot Node Classification by Node-Level Graph Diffusion

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

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation

Who's Your Judge? On the Detectability of LLM-Generated Judgments

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

SCALE: Augmenting Content Analysis via LLM Agents and AI-Human Collaboration

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning

GraphRCG: Self-Conditioned Graph Generation

FairSkin: Fair Diffusion for Skin Disease Image Geneartion