KCKezhen Chen

Kezhen Chen

*This is an algorithmically generated author record based on publicly available information.

Kezhen Chen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues

    by Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang

    Although the Retrieval-Augmented Generation (RAG) paradigms can use external knowledge to enhance and ground the outputs of Large Language Models (LLMs) to mitigate generative hallucinations and static knowledge base problems, they still suffer from limited flexibility in adopting Information Retrieval (IR) systems with varying capabilities, constrained interpretability during the multi-round retrieval process, and a lack of end-to-end optimization. To address these challenges, we propose a novel LLM-centric approach, IM-RAG, that integrates IR systems with LLMs to support multi-round RAG through learning Inner Monologues (IM, i.e., the human inner voice that narrates one's thoughts). During the IM process, the LLM serves as the core reasoning model (i.e., Reasoner ) to either propose queries to collect more information via the Retriever or to provide a final answer based on the conversational context. We also introduce a Refiner that improves the outputs from the Retriever, effectively bridging the gap between the Reasoner and IR modules with varying capabilities and fostering multi-round communications. The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards, and the answer prediction is further separately optimized via Supervised Fine-Tuning (SFT). We conduct extensive experiments with the HotPotQA dataset, a popular benchmark for retrieval-based, multi-step question-answering. The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules as well as strong interpretability exhibited in the learned inner monologue.


  • Constructing a semi-artificial photosynthetic system for the removal of trichloroethylene by visible light-driven obligate organohalide-respiring bacteria

    by Qing Tang, Qijun Tang, Jiawei Yang, Kezhen Chen, Haiqiang Wang, Chaofeng Shen

    发展新型绿色、高效、低能耗和可持续的微生物修复技术用于处理氯代烯烃污染十分必要。专性有机卤化物呼吸菌能专一高效地去除氯代有机污染物,但在实际修复过程中电子供体如氢气的不足限制了其应用,因此寻找合适的供氢方式十分重要。利用光催化水解产氢为微生物提供电子供体可能是一种理想方式,然而国内外尚未有半人工光合系统驱动微生物脱卤呼吸的相关研究。本文利用脱卤拟球菌Dehalococcoides mccartyi 菌株195(Dhc195)与硼掺杂石墨相氮化碳纳米片构建了B-C3N4-NS-Dhc195生物杂化体系,探究可见光驱动其对三氯乙烯(TCE)进行厌氧还原脱氯的可行性。研究结果表明,在25 ± 5 W∙m−2的低强度可见光下该生物杂化体系可持续稳定地将TCE逐步还原脱氯至乙烯(ETH),脱氯速度为1.13 ± 0.13 μmol∙L−1∙day−1;该杂化体系内检测到氢气生成,对Dhc195脱氯的用氢量进行衡算,其氢气利用率达84%。这表明可见光下光催化剂分解水产氢,脱氯菌利用氢气作为电子供体还原TCE,从而实现可见光驱动微生物脱卤呼吸。本研究率先提出了一种间接利用光能实现微生物处理氯代有机污染物的方法,对氯代有机污染物的绿色、低碳、可持续治理和修复具有启发意义。


  • Enhancement of perchloroethene dechlorination by a mixed dechlorinating culture via magnetic nanoparticle-mediated isolation method

    by Kezhen Chen, Zefan Liu, Xiaomin Wang, Chungui Yu, Junxiang Ye, Chunna Yu, Feier Wang, Chaofeng Shen