Yohan Jo

ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents

Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs

Non-Collaborative User Simulators for Tool Agents

PTCG: Persona-guided Tree-based Counterargument Generation

SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings

DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents

Future Policy Aware Preference Learning for Mathematical Reasoning

Towards Robust Benchmark of Object Hallucination on Multiple Images

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions

ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models

DialSim: A Real-Time Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents