List of Publications (by Year)
2026
- Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers.
Yu Wang, Shengyao Zhuang, Xueguang Ma, Zongyu Wu, Jimmy Lin, Vivek Srikumar, and Zhichao Xu.
arXiv preprint [preprint]
- Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget.
Zhichao Xu, Xueguang Ma, Shengyao Zhuang, Luyu Gao, Wenqian Ye, Yu Wang, Jamie Callan, and Jimmy Lin.
arXiv preprint [preprint]
- VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models.
Zhiqi Huang, Vivek Datla, Zhichao Xu, Puxuan Yu, Vivek Srikumar, and Alfy Samuel.
EMNLP 2026 Main
- CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection.
Lingbo Liu, Guande Wu, Han Ding, Yawei Wang, Qiang Zhou, Yuzhe Lu, Zhichao Xu, Huan Song, Panpan Xu, and Lin Lee Cheong.
EMNLP 2026 Main [preprint]
- Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion.
Maitrey Mehta, Nishant Subramani, Zhichao Xu, Ashim Gupta, and Vivek Srikumar.
COLM 2026 [preprint]
- LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum.
Zhichao Xu, Shengyao Zhuang, Crystina Zhang, Xueguang Ma, Yijun Tian, Maitrey Mehta, Jimmy Lin, and Vivek Srikumar.
SIGIR 2026 [pdf]
- Layer-wise Token Compression for Efficient Document Reranking.
Shengyao Zhuang, Zhichao Xu, and Ivano Lauriola.
SIGIR 2026 [pdf]
- Rethinking On-policy Optimization for Query Augmentation.
Zhichao Xu et al.,
TMLR 2026 [pdf]
- Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation.
Zhichao Xu*, Zongyu Wu*, et al.,
TMLR 2026 [pdf]
- A Survey of Model Architectures for Information Retrieval.
Zhichao Xu, Fengran Mo, Zhiqi Huang, Crystina Zhang, Puxuan Yu, Bei Wang, Jimmy Lin, Vivek Srikumar.
TMLR 2026 [pdf]
- PERSONAJUDGE: Simulating Individual Human Preference Judgments with Human-Centered Demonstration Data.
Zeyu He, Xuan Qi, Subramanian Chidambaram, Zhichao Xu, Vinayak Arannil, Lydia Chilton, Alex C. Williams
SIGDIAL 2026 [pdf]
- Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing.
Yiming Liu, Ziyue Zhang, Zhichao Xu, Xin Yu, Yingheng Tang, Tianyu Jiang, and Jie Cao
SIGDIAL 2026 [pdf]
- Teaching People LLM's Errors and Getting it Right.
Nathan Stringham, Fateme Hashemi Chaleshtori, Xinyuan Yan, Zhichao Xu, Bei Wang, and Ana Marasovic.
TrustNLP 2026 [pdf]
- TransactionGPT: Toward Foundational Transaction Modeling.
Yingtong Dou, Zhimeng Jiang, Tianyi Zhang, Mingzhi Hu, Zhichao Xu, et al.,
KDD 2026 ADS Track [preprint]
- Reinforcement Learning for Self-Improving Agent with Skill Library
Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong
ACL 2026 Main [pdf]
- Reinforcement Mid-Training.
Yijun Tian, Shaoyu Chen, Zhichao Xu, Yawei Wang, Jinhe Bi, Peng Han, Wei Wang.
ICLR 2026 [pdf]
- Learning to Ideate for Machine Learning Engineering Agents.
Yunxiang Zhang, Kang Zhou, Zhichao Xu, Kiran Ramnath, Yun Zhou, Sangmin Woo, Haibo Ding, Lin Lee Cheong.
EACL 2026 Main [pdf]
- BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation
Bo Yuan, Yun Zhou, Zhichao Xu, Kiran Ramnath, Aosong Feng, Balasubramaniam Srinivasan.
EACL 2026 Findings [pdf]
- SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
Jiazheng Li, Yawei Wang, David Yan, Yijun Tian, Zhichao Xu, Huan Song, Panpan Xu, Lin Lee Cheong.
EACL 2026 Findings [pdf]
- Diffusion Language Model Inference with Monte Carlo Tree Search
Huang et al.,
EACL 2026 Findings [pdf]
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval.
Fengran Mo, Jinghan Zhang, Yuchen Hui, Jia Ao Sun, Zhichao Xu, Zhan Su, Jian-Yun Nie.
AAAI 2026 [pdf]
- Balancing Heterogeneous Knowledge Sources: Pareto-Based Multi-Teacher Distillation for MLPs on Graphs.
Wenrui Zhao, Yijun Tian, Zhichao Xu, Yawei Wang, Chuxu Zhang.
AAAI 2026 [pdf]
2025
- RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation.
Zhichao Xu*, Minheng Wang*, et al.,
arXiv preprint [pdf]
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications.
Minhua Lin, Zongyu Wu, Zhichao Xu, Hui Liu, Xianfeng Tang, Qi He, Charu Aggarwal, Hui Liu, Xiang Zhang, Suhang Wang.
arXiv preprint [pdf]
- Reinforcement Learning to Rank Using Coarse-grained Rewards.
Yiteng Tu, Zhichao Xu, Tao Yang, Weihang Su, Yujia Zhou, Yiqun Liu, Fen Lin, Qin Liu, Qingyao Ai.
arXiv preprint [pdf]
- CSPLADE: Learned Sparse Retrieval with Causal Language Models.
Zhichao Xu, Aosong Feng, Yijun Tian, Haibo Ding and Lin Lee Cheong.
IJCNLP-AACL 2025 Main [pdf]
- Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate.
Ashim Gupta, Maitrey Mehta, Zhichao Xu and Vivek Srikumar.
IJCNLP-AACL 2025 Main [pdf]
- Distillation versus Contrastive Learning: How to Train Your Rerankers.
Zhichao Xu, Zhiqi Huang, Shengyao Zhuang, and Vivek Srikumar.
IJCNLP-AACL 2025 Findings [pdf]
- IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs.
Aosong Feng*, Balasubramaniam Srinivasan*, Yun Zhou*, Zhichao Xu*, et al.,
EMNLP 2025 Industry Track [pdf]
- SLOT: Structuring the Output of Large Language Models.
Darren Wang*, Zhengyuan Shen*, Soumya Mishra, Zhichao Xu, Yifei Teng and Haibo Ding.
EMNLP 2025 Industry Track [pdf]
- A Systematic Survey of Automatic Prompt Optimization Techniques.
Ramnath et al.,
EMNLP 2025 Main [pdf]
- MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation.
Chang et al.,
ACL 2025 Main [pdf]
- State Space Models are Strong Text Rerankers.
Zhichao Xu*, Jinghua Yan*, Ashim Gupta and Vivek Srikumar.
RepL4NLP 2025 [pdf]
2024
- RankMamba: Benchmarking Benchmarking Mamba's Document Ranking Performance in the Era of Transformers.
Zhichao Xu.
arXiv preprint [pdf]
- Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression.
Zhichao Xu, Ashim Gupta, Tao Li, Oliver Bentham and Vivek Srikumar.
Findings of EMNLP 2024 [pdf]
- Multi-dimensional Evaluation of Empathetic Dialogue Utterances.
Zhichao Xu and Jiepu Jiang.
Findings of EMNLP 2024 [pdf]
- Counterfactual Editing for Search Result Explanation.
Zhichao Xu, Hemank Lamba, Qingyao Ai, Joel Tetreault and Alex Jaimes.
ICTIR 2024 [pdf]
- Interaction-level Membership Inference Attack against Recommender Systems with Long-tailed Distribution.
Da Zhong, Xiuling Wang, Zhichao Xu, Jun Xu, Wendy Hui Wang.
CIKM 2024 [pdf]
- In-Context Example Ordering Guided by Label Distributions.
Zhichao Xu, Daniel Cohen, Bei Wang and Vivek Srikumar.
Findings of NAACL 2024 [pdf]
- An In-depth Investigation of User Simulation for Conversational Search.
Zhenduo Wang, Zhichao Xu, Qingyao Ai and Vivek Srikumar.
TheWebConf 2024 [pdf]
2023
- Context-aware Decoding Reduces Hallucination in Query-focused Summarization.
Zhichao Xu.
arXiv preprint [pdf]
- A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability.
Zhichao Xu, Hansi Zeng, Juntao Tan, Zuohui Fu, Yongfeng Zhang and Qingyao Ai.
ACM Transactions on Information Systems (TOIS) [pdf]
- Automated Generation of Security-centric Descriptions for Smart Contract Bytecode.
Yu Pan, Zhichao Xu, Levi Taiji Li, Yunhe Yang and Mu Zhang.
ISSTA 2023 [pdf] Distinguished Paper Award
- A Lightweight Constrained Generation Alternative for Query-focused Summarization.
Zhichao Xu and Daniel Cohen.
SIGIR 2023 [pdf]
- FARA, Future-aware Ranking Algorithm for Fairness Optimization.
Tao Yang, Zhichao Xu, Zhenduo Wang and Qingyao Ai.
CIKM 2023 [pdf]
- Marginal-Certainty-aware Fair Ranking Algorithm.
Tao Yang, Zhichao Xu, Zhenduo Wang, Anh Tran and Qingyao Ai.
WSDM 2023 [pdf]
- Vertical Allocation-based Fair Exposure Amortizing in Ranking.
Tao Yang, Zhichao Xu and Qingyao Ai.
SIGIR AP 2023 [pdf] Best Paper Finalist
Prior to 2023
- Learning to Rank Rationales for Explainable Recommendation.
Zhichao Xu, Yi Han, Tao Yang, Anh Tran and Qingyao Ai.
arXiv preprint [pdf]
- Understanding the Effectiveness of Reviews in E-commerce Recommendation.
Zhichao Xu, Hansi Zeng and Qingyao Ai.
ICTIR 2021 [pdf]
- A Zero Attentative Relevance Matching Network for Review Modeling in Recommnder System.
Hansi Zeng, Zhichao Xu and Qingyao Ai.
ECIR 2021 [pdf]
- E-commerce Recommendation with Weighted Expected Utility.
Zhichao Xu, Yi Han, Yongfeng Zhang and Qingyao Ai.
CIKM 2020 [pdf]
- Speech-based Activity Recognition for Trauma Resuscatation.
Jalal Abdulbaqi, Yue Gu, Zhichao Xu, Chenyang Gao, Ivan Marsic and Randall Burd.
ICHI 2020 [pdf]