Xiaoshuai Song (宋晓帅)  Master Student Room 731, 3rd Teaching Building Dept. of Artificial Intelligence Beijing University of Posts and Telecommunications (BUPT) Beijing, China, 100084. Email: songxiaoshuai@bupt.edu.cn [Semantic Scholar]

Biography

I am a second-year master student of Pattern Recognition and Intelligent System Laboratory in the Department of Artificial Intelligence, Beijing University of Posts and Telecommunications(BUPT), advised by Prof. Weiran Xu. Previously, I received my B.S. degree from the Department of Information and Communication Engineering, Beijing University of Posts and Telecommunications in July, 2022.

I used to focus on Out-of-domain Intent Mining (Detection, Discovery,Increment) in Dialog System. Currently, my research interests focuses on external knowledge-enhanced LLMs, including retrieval-augmented knowledge editing and retrieval-augmented generation, as well as exploring the capabilities of LLMs.

News

• [2024-06] We propose CS-Bench, the first benchmark dedicated to evaluating the performance of LLMs in computer science! See more details.

Experiences

Academia

• [2022.9 - Now] M.S. at Beijing University of Posts and Telecommunications
• [2018.9 - 2022.6] B.S. at Beijing University of Posts and Telecommunications

Industry

• [2024.7 - Now] Alibaba, Taotian - Future Life Lab, LLM Algorithm Research Intern.
• [2023.7 - 2024.6] SenseTime, Research Institute - NLP, Algorithm Research Intern.

Publications

(* denotes equal contributions)
-2024-

• Faceptor: A Generalist Model for Face Perception
  Lixiong Qin, Mei Wang, Xuannan Liu, Yuhang Zhang, Wei Deng, Xiaoshuai Song, Weiran Xu, and Weihong Deng
  ECCV 2024. [paper]

• Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
  Pei Wang, Keqing He, Yejie Wang, Xiaoshuai Song, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  COLING 2024. [paper]

• Noise-BERT: A Unified Perturbation-robust Framework With Noise Alignment Pre-training For Noisy Slot Filing Task
  Jinxu Zhao, Guanting Dong, Yueyan Qiu, Tingfeng Hui, Xiaoshuai Song, Daichi Guo, Weiran Xu
  ICASSP 2024. [paper]

-2023-

• Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
  Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  Main Conference of EMNLP 2023. [paper]

• Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition
  Xiaoshuai Song, Yutao Mou, Keqing He, Yueyan Qiu, Pei Wang, Weiran Xu
  Findings of EMNLP 2023. [paper]

• APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
  Pei Wang, Keqing He, Yutao Mou, Xiaoshuai Song, Yanan Wu, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
  Findings of EMNLP 2023. [paper]

• Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
  Yutao Mou, Xiaoshuai Song*, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu
  Main Conference of ACL 2023. [paper]

Preprints

• We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
  Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, Honggang Zhang
  Arxiv 24.07. [paper] [website]

• CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
  Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma GongQue, Jianing Yu, Qiuna Tan, Weiran Xu
  Arxiv 24.06. [paper] [website]

• Knowledge Editing on Black-box Large Language Models
  Xiaoshuai Song, Zhengyang Wang, Keqing He, Guanting Dong, Jinxu Zhao, Weiran Xu
  Arxiv 24.02. [paper]

• Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
  Jiachi Liu, Liwen Wang, Guanting Dong, Xiaoshuai Song, Zechen Wang, Zhengyang Wang, Shanglin Lei, Jinzheng Zhao, Keqing He, Bo Xiao, Weiran Xu
  Arxiv 23.10. [paper]

Honors & Awards

• Outstanding Master Students (Top 5%), BUPT. 2023.10
• Excellent First-class Scholarship for Master Students, BUPT. (Two times) 2022, 2023
• Chinese College Student Mathematics Competition (Preliminary round), First Prize, 2022.01
• MathorCup University Mathematical Modeling Challenge, Second Prize, 2021.03
• The Mathematical Contest in Modeling, Honorable Mention, 2020.4

Services

Reviewer for:

• ACL ARR

© 2024 Xiaoshuai Song