CV

Education

• Ph.D in Big Data Science and Engineering, Renmin University of China, 2024
  • Advisor: Ji-Rong Wen and Wayne Xin Zhao
• M.S. in Software Engineering, Peking University, 2020
  • Advisor: Jingsong Yu
• B.S. in Harbor Waterway and Coastal Engineering, Hohai University, 2017
  • Advisor: Jian Shi

Work experience

• NLC Group, MSRA: Research Intern
  • Apr 2022 - Now
  • Research Directions: Pre-trained Language Model and Dense Retrieval
  • Advisor: Yeyun Gong and Nan Duan
• iFLYTEK Research: Research Intern
  • Sep 2021 - Apr 2022
  • Research Directions: Pre-trained Language Model and Mathematical Logical Reasoning
  • Advisor: Jing Sha and Shijin Wang
• Meituan NLP Center: Research Intern
  • Dec 2019 - May 2021
  • Research Directions: Conversational Recommender System and Recommender System
  • Advisor: Fuzheng Zhang and Zhongyuan Wang
• Microsoft XiaoIce Group: Research Intern
  • Aug 2019 - June 2020
  • Research Directions: Dialog System
  • Advisor: Kai Zhang and Yu Wu

Awards and Honors

• EACL 2024 Evaluation and Model Insight Award Link
• 2022 Bytedance Scholarship (10 PhD Students in China Mainland) Link
• 2022 MSRA Fellowship (12 PhD Students in Asia-Pacific-region) Link
• 2022 Baogang Scholarship (12 Students in RUC).
• 2022 National Scholarship.
• LIC2021 Multi-Skill Dialog Challenge Link
  • Ranked 1st in Automatic Metrics Track, 3rd in Human Evaluation Track
• LIC2020 Conversational Recommendation Challenge Link
  • Ranked 2st in Automatic Metrics Track, 4rd in Human Evaluation Track
• 2018 Jane Street Electronic Trading Challenges
  • Ranked 1st
• 2018 The Data Open Challenges Citadel Datathen
  • Ranked 2nd
• 2016 American Mathematical Contest in Modeling
  • Honorable Mention
• 2015 China Undergraduate Mathematical Contest in Modeling
  • National Second Prize
• 2015 National Zhou Peiyuan college student mechanics competition
  • National Third Prize
• 2015 Jiangsu Province Undergraduate Mechanical Competition
  • The First Prize

Publications

Unsupervised Context Rewriting for Open Domain Conversation

Improving Multi-turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting

Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization

Leveraging historical interaction data for improving conversational recommender system

Multi-modal knowledge graphs for recommender systems

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

Towards Topic-Guided Conversational Recommender System

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Neural Sentence Ordering Based on Constraint Graphs

Content Selection Network for Document-grounded Retrieval-based Chatbots

BERT4SO: Neural Sentence Ordering by Fine-tuning BERT

A Novel Macro-Micro Fusion Network for User Representation Learning on Mobile Apps

Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System

Contrastive Curriculum Learning for Sequential User Behavior Modeling via Data Augmentation

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models

C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System

Filter-enhanced MLP is All You Need for Sequential Recommendation

Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network

Debiased Contrastive Learning of Unsupervised Sentence Representations

Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-N Recommendation

Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval

Enhancing Multi-View Smoothness for Sequential Recommendation Models

UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

Improving News Recommendation via Bottlenecked Multi-task Pre-training

Diffusion Models for Non-autoregressive Text Generation: A Survey

Visually-augmented Pretrained Language Models for NLP Tasks without Images

Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization

Improving Conversational Recommendation Systems via Counterfactual Data Simulation

JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving

MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers

Learning to Perturb for Contrastive Learning of Unsupervised Sentence Representations

Alleviating the Long-Tail Problem in Conversational Recommender Systems

ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

StructGPT: A General Framework for Large Language Model to Reason over Structured Data

Evaluating Object Hallucination in Large Vision-Language Models

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning

Improving large language models via fine-grained reinforcement learning with minimum editing constraint

MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels

Images are Achilles’ Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models

Low-Redundant Optimization for Large Language Model Alignment

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

LLMBox: A Comprehensive Library for Large Language Models

Service

• IJCAI 2021
  • Senior PC Reviewer
• AAAI 2021, KDD 2021, TOIS 2021, WSDM 2022, KDD 2022, EMNLP 2022, COLING 2022, TOIS 2022
  • PC Reviewer