Publications

2024

15. JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework. [PDF][Code]
    Fan Liu, Yue Feng, Zhao Xu, Lixin Su, Xinyu Ma, Dawei Yin, Hao Liu
    Arxiv

14. MAIR: A Massive Benchmark for Evaluating Instructed Retrieval. [PDF][Code]
    Weiwei Sun, Zhengliang Shi, Jiulong Wu, Lingyong Yan, Xinyu Ma, Yiding Liu, Min Cao, Dawei Yin, Zhaochun Ren
    EMNLP'2024 Main

13. Understanding the Collapse of LLMs in Model Editing. [PDF]
    Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Du Su, Dawei Yin, Huawei Shen
    EMNLP'2024 Findings

12. The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse. [PDF][Code][Website]
    Wanli Yang, Fei Sun, Xinyu Ma, Xun Liu, Dawei Yin, Xueqi Cheng
    ACL'2024 Findings

2023

11. Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers. [PDF][Code]
    Weiwei Sun, Zheng Chen, Xinyu Ma, Lingyong Yan, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren
    Arxiv 2023

10. Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval. [PDF][Code]
    Xiaojie Sun, Keping Bi, Jiafeng Guo, Xinyu Ma, Fan Yixing, Hongyu Shan, Qishen Zhang, Zhongyi Liu
    CIKM'2023, (Short Paper)
    

9. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. [PDF][Code]
   Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren
   EMNLP'2023 (Full Paper) Outstanding Paper Award
   

2022

8. Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval. [PDF][Slides]
   Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xueqi Cheng.
   CIKM'2022, (Full Paper)
   
9. A Contrastive Pre-training Approach to Discriminative Autoencoder for Dense Retrieval [PDF]
   Xinyu Ma, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng.
   CIKM'2022, (Short Paper)
   

2021

6. Pre-training Methods in Information Retrieval. [PDF][Code]
   Yixing Fan^*, Xiaohui Xie^*, Yinqiong Cai, Jia Chen, Xinyu Ma, Xiangsheng Li, Ruqing Zhang, Jiafeng Guo. (^*Equal contribution)
   Foundations and Trends® in Information Retrieval. (I wrote Section 4 and Section 6.)
   
7. Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction. [PDF][Code][Slides][Video]
   Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xueqi Cheng.
   SIGIR'2022, (Full Paper, Acceptance Rate = 20%)
   

2020

4. B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval. [PDF][Code][Slides][Video]
   Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixin Fan, Yingyan Li, Xueqi Cheng.
   SIGIR'2021, (Full Paper, Acceptance Rate = 21%)
   
5. PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval. [PDF][Code][Slides][Video]
   Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixin Fan, Xiang Ji, Xueqi Cheng.
   WSDM'2021, (Full Oral Paper, Acceptance Rate = 18.6%)
   
6. A Linguistic Study on Relevance Modeling in Information Retrieval. [PDF][Video]
   Yixin Fan, Jiafeng Guo, Xinyu Ma, Ruqing Zhang, Yanyan Lan, Xueqi Cheng.
   WWW'2021, (Full Paper, Acceptance Rate = 20.6%)
   
7. 关于短文本匹配的泛化性和迁移性的研究分析(An Empirical Investigation of Generalization and Transfer in Short Text Matching). [PDF]
   Xinyu Ma, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Lixin Su, Xueqi Cheng.
   计算机研究与发展'2021, (CCF A 中文期刊)