Wenting Zhao

This research focuses on improving question reformulation for better user interactions.

A new benchmark evaluates LLMs for factual accuracy.

Explore the need for an open feedback system to improve AI responses.

Language models excel at memory tasks but struggle with reasoning challenges.

A tool to analyze chat logs quickly and effectively for researchers.

Research focuses on improving language models' ability to understand longer texts.

Large Language Models enhance code summarization assessments with creative evaluations.

Examining issues in community-driven chatbot evaluations and ways to improve them.