Lanrui Wang (王岚睿)

I am currently pursuing a Master's degree at Institute of Information Enginering, Chinese Academy of Sciences in Beijing, under the guidance of Prof. Zheng Lin. Currently, I am a research intern at the Meituan NLP Center. Previously, I had the privilege of working as a research intern at the Pattern Recognition Center (PRC), WeChat AI at Tencent, under the supervision of Fandong Meng 2021-2022.

My research interests include long-context LLMs, dialogue generation, and related applications. Please reach out to me via email: wanglanrui@iie.ac.cn.

Google Scholar  /  Github

• [Nov. 2024] One paper accepted to COLING 2025.
• [Oct. 2023] One paper accepted to EMNLP 2023.
• [Oct. 2022] One paper accepted to EMNLP 2022.
• [Sep. 2022] I joined the Institute of Information Engineering, UCAS as a Master student.
• [Oct. 2021] I joined the PRC, served as a research intern WeChat AI at Tencent, supervised by Fandong Meng.
• [Jun. 2022] I received B.Eng. from School of Computer Science, Beijing University of Posts and Telecommunications. GPA: 3.71/4.0

Google Scholar / DBLP

(*: Equal contribution)

Current commonsense knowledge derived from dialogue contexts is inherently limited and often fails to adequately anticipate the future course of a dialogue. This lack of foresight can mislead LLMs and hinder their ability to provide effective support. In response to this challenge, we present an innovative framework named Sensible and Visionary Commonsense Knowledge (Sibyl).

For Empathetic Dialogue Generation task, emotions change dynamically between utterances, which makes previous works difficult to perceive the emotion flow and predict the correct emotion of the target response, leading to inappropriate response. In this work, we improved not only the ability to recognize contextual emotions, but also the ability to filter out unreasonable external knowledge, allowing the model to generate more sensible empathetic responses.

Design and source code from Jon Barron's website