Publications

2026

13. AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generation [PDF][Code]
    Zhihui Yao, Hengran Zhang, Keping Bi
    

12. Training Dense Retrievers with Multiple Positive Passages[PDF]
    Benben Wang, Minghao Tang, Hengran Zhang, Jiafeng Guo, Keping Bi
    

11. Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality[PDF]
    Jiahan Chen, Da Li, Hengran Zhang, Yinqiong Cai, Lixin Su, Jiafeng Guo, Daiting Shi, Dawei Yin, Keping Bi
    

10. Bagging-Based Model Merging for Robust General Text Embeddings[PDF][Code]
    Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Wenbo Yang, Daiting Shi, Xueqi Cheng
    

2025

9. LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation[PDF][Code]
   Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
   

8. Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation[PDF][Code]
   Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
   SIGIR-AP25

7. A Comparative Study of Specialized LLMs as Dense Retrievers[PDF][Code]
   Hengran Zhang, Keping Bi, Jiafeng Guo
   CCIR 25

6. Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation [PDF][Code]
   Hengran Zhang, Minghao Tang, Keping Bi, Jiafeng Guo, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng
   EMNLP 25

5. Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling [PDF][Code]
   Hengran Zhang, Keping Bi, Jiafeng Guo, Xiaojie Sun, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng
   

2024

4. Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy [PDF][Code]
   Hengran Zhang,Keping Bi, Jiafeng Guo, Xueqi Cheng
   

3. Are Large Language Models Good at Utility Judgments? [PDF][Code]
   Hengran Zhang,Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
   SIGIR 2024

2023

2. From relevance to utility: evidence retrieval with feedback for fact verification [PDF][Code]
   Hengran Zhang,Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
   EMNLP 2023
   

2022

1. Cort: A new baseline for comparative opinion classification by dual prompts [PDF][Code]
   Yequan Wang, Hengran Zhang, Aixin Sun, Xuying Meng.
   EMNLP2022