Hui Liu

Hui Liu (刘晖)

Email: huiliulayne@gmail.com

[Publications] [Projects] [Miscellaneous]

About Me

Hi! My name is Hui Liu. I am a Senior Applied Scientist at Amazon Ads. I obtained my Ph.D. degree from the Department of Electrical and Computer Engineering at Queen's University. Prior to that, I received my B.S. from the School of Electronics Engineering and Computer Science at Peking University in 2018.

Back in my third year of undergrad, when I was tinkering with SVMs for my first research project, I could never have imagined witnessing the shift in natural language processing from RNNs to Transformers. Now I feel fortunate to witness the impressive power of LLMs driving the new trends in NLP research. Recently, the question I think a lot is - what is reasoning?

News

Experience

Academic Services

Publication/Preprint
[ All | 2026 | 2025 | 2024 and before | Preprint ]

**Please refer to my Google Scholar Page for a complete list.

    2026

  1. Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization
    Yu Fu, Chen Luo, Josef Valvoda, Xin Zhang, Xuejing Lei, Xiao Pan, Hui Liu, Yue Dong
    ACL 2026, long paper

  2. To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
    Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He
    ACL 2026, long paper

  3. Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
    Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong
    Findings of ACL 2026, long paper

  4. Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations
    Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, Yujun Zhang
    Findings of ACL 2026, long paper

  5. A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning
    Yingqian Cui, Zhenwei Dai, Pengfei He, Bing He, Hui Liu, Zhan Shi, Xianfeng Tang, Jingying Zeng, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin
    Findings of ACL 2026, long paper

  6. MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
    Xiao Lin, Zhining Liu, Ze Yang, Gaotang Li, Ruizhong Qiu, Shuke Wang, Hui Liu, Haotian Li, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong
    ICML 2026

  7. From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
    Juncheng Wu, Hardy Chen, Haoqin Tu, Xianfeng Tang, Freda Shi, Hui Liu, Hanqing Lu, Cihang Xie, Yuyin Zhou
    ICML 2026

  8. When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
    Yahong Wang, Juncheng Wu, Zhangkai Ni, Longzhen Yang, Yihang Liu, Chengmei Yang, Ying Wen, Lianghua He, Xianfeng Tang, Hui Liu, Yuyin Zhou
    CVPR 2026

  9. How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
    Minhua Lin, Enyan Dai, Hui Liu, Xianfeng Tang, Yuliang Yan, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Fali Wang, Hongcheng Gao, Chen Luo, Xiang Zhang, Qi He, Suhang Wang
    ICLR 2026

  10. Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
    Zhining Liu, Ziyi Chen, Hui Liu, Chen Luo, Xianfeng Tang, Suhang Wang, Joy Zeng, Zhenwei Dai, Zhan Shi, Tianxin Wei, Benoit Dumoulin, Hanghang Tong
    ICLR 2026

  11. Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
    Zhiwei Zhang, Hui Liu, Xiaomin Li, Zhenwei Dai, Jingying Zeng, Fali Wang, Minhua Lin, Ramraj Chandradevan, Zhen Li, Chen Luo, Xianfeng Tang, Qi He, Suhang Wang
    ICLR 2026

  12. Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
    Zhiwei Zhang, Xiaomin Li, Yudi Lin, Hui Liu, Ramraj Chandradevan, Linlin Wu, Minhua Lin, Fali Wang, Xianfeng Tang, Qi He, Suhang Wang
    ICLR 2026

  13. TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
    Pengfei He, Zhenwei Dai, Bing He, Hui Liu, Xianfeng Tang, Hanqing Lu, Juanhui Li, Jiayuan Ding, Subhabrata Mukherjee, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin
    ICLR 2026

  14. Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
    Xiaoke Huang, Ningsen Wang, Hui Liu, Xianfeng Tang, Yuyin Zhou
    ICLR 2026

  15. DiffKGW: Stealthy and Robust Diffusion Model Watermarking
    Tianxin Wei, Ruizhong Qiu, Yifan Chen, Yunzhe Qi, Jiacheng Lin, Wenxuan Bao, Wenju Xu, Sreyashi Nag, Ruirui Li, Hanqing Lu, Zhengyang Wang, Chen Luo, Hui Liu, Suhang Wang, Jingrui He, Qi He, Xianfeng Tang
    Transactions on Machine Learning Research (TMLR), 2026

  16. Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
    Yu Fu, Haz Sameen Shahgir, Hui Liu, Xianfeng Tang, Qi He, Yue Dong
    AAAI 2026

    17. 2025

  17. SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
    Hardy Chen, Haoqin Tu, Fali Wang, Hui Liu, Xianfeng Tang, Xinya Du, Yuyin Zhou, Cihang Xie
    Transactions on Machine Learning Research (TMLR), 2025

  18. AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
    Fali Wang, Hui Liu, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Zongyu Wu, Chen Luo, Zhen Li, Xianfeng Tang, Qi He, Suhang Wang
    NeurIPS 2025

  19. Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
    Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C Aggarwal, Hui Liu
    NeurIPS 2025

  20. Efficient Long CoT Reasoning in Small Language Models
    Zhaoyang Wang, Jinqi Jiang, Tian Qiu, Hui Liu, Xianfeng Tang, Huaxiu Yao
    NeurIPS 2025 Workshop on Efficient Reasoning

  21. m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
    Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, Yuyin Zhou
    Machine Learning for Health Symposium (ML4H), 2025

  22. MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
    Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, Yuyin Zhou
    Machine Learning for Health Symposium (ML4H), 2025

  23. Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack
    Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, Suhang Wang
    EMNLP 2025, long paper

  24. Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
    Jiankun Zhang, Shenglai Zeng, Jie Ren, Tianqi Zheng, Hui Liu, Xianfeng Tang, Hui Liu, Yi Chang
    EMNLP 2025, long paper

  25. ViLBench: A Suite for Vision-Language Process Reward Modeling
    Haoqin Tu, Weitao Feng, Hardy Chen, Hui Liu, Xianfeng Tang, Cihang Xie
    EMNLP 2025, long paper

  26. Automatic Task-aware Instruction Optimizer for Black-box LLMs
    Yunzhe Qi, Jinjin Tian, Ruirui Li, Tianci Liu, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He
    Findings of EMNLP 2025, long paper

  27. In-Context Personalized Alignment with Feedback History under Counterfactual Evaluation
    Xisen Jin, Zheng Li, Zhenwei DAI, Hui Liu, Xianfeng Tang, Chen Luo, Rahul Goutam, Xiang Ren, Qi He
    ICML 2025 MoFA Workshop, long paper

  28. EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
    Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song
    ACL 2025, long paper

  29. Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
    Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
    Findings of ACL 2025, long paper

  30. Divide-Verify-Refine: Aligning LLM Responses with Complex Instructions
    Xianren Zhang, Xianfeng Tang, Hui Liu, Zongyu Wu, Qi He, Dongwon Lee, Suhang Wang
    Findings of ACL 2025, long paper

  31. Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
    Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Hui Liu, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang
    Findings of ACL 2025, long paper

  32. A General Framework to Enhance Fine-tuning-based LLM Unlearning
    Jie Ren, Zhenwei Dai, Xianfeng Tang, Hui Liu, Jingying Zeng, Zhen Li, Rahul Goutam, Suhang Wang, Yue Xing, Qi He
    Findings of ACL 2025, long paper

  33. Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
    Tianci Liu, Ruirui Li, Zihan Dong, Hui Liu, Xianfeng Tang, Qingyu Yin, Linjun Zhang, Haoyu Wang, Jing Gao
    ICML 2025

  34. Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
    Jingying Zeng, Zhenwei Dai, Hui Liu, Samarth Varshney, Zhiji Liu, Chen Luo, Zhen Li, Qi He, Xianfeng Tang
    SIGIR 2025 SIRIP (Industry Track) track

  35. Catastrophic Failure of LLM Unlearning via Quantization
    Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu, Xianfeng Tang, Hui Liu, Qi He, Wenpeng Yin, Suhang Wang
    ICLR 2025
    36. [code] [Hacker News]
  36. Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
    Tianci Liu, Ruirui Li, Haoyu Wang, Yunzhe Qi, Hui Liu, Xianfeng Tang, Tianqi Zheng, Qingyu Yin, Monica Cheng, Jun Huan, Jing Gao
    ICLR 2025

  37. SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
    Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C Ho, Carl Yang, Qi He
    NAACL 2025, long paper

  38. Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
    Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang
    NAACL 2025, long paper

  39. Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data
    Juanhui Li, Sreyashi Nag, Hui Liu, Xianfeng Tang, Sheikh Sarwar, Limeng Cui, Hansu Gu, Suhang Wang, Qi He, Jiliang Tang
    Findings of NAACL 2025, long paper

    40. 2024 and before

  40. Exploring Query Understanding for Amazon Product Search
    Chen Luo, Xianfeng Tang, Hanqing Lu, Yaochen Xie, Hui Liu, Zhenwei Dai, Limeng Cui, Ashutosh Joshi, Sreyashi Nag, Yang Li, Zhen Li, Rahul Goutam, Jiliang Tang, Haiyang Zhang, Qi He
    IEEE BigData'24, full paper

  41. Knowledge-Selective Pretraining for Attribute Value Extraction
    Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Yang Wang, Xiaodan Zhu
    Findings of EMNLP 2023, long paper

  42. Interpretable Low-Resource Legal Decision Making
    Rohan Bhambhoria, Hui Liu, Samuel Dahan, Xiaodan Zhu
    AAAI 2022 AI for Social Impact Track, full paper

  43. Unsupervised Conversation Disentanglement through Co-Training
    Hui Liu, Zhan Shi, Xiaodan Zhu
    EMNLP 2021 main conference, long paper
    44. [code]
  44. Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
    Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li and Xiaodan Zhu
    Findings of EMNLP 2021, long paper

  45. Descriptive Image Captioning with Salient Retrieval Priors
    Zhan Shi, Hui Liu, Xiaodan Zhu
    Canadian Conference on Artificial Intelligence 2021, full paper

  46. Enhancing Descriptive Image Captioning with Natural Language Inference
    Zhan Shi, Hui Liu, Xiaodan Zhu
    ACL-IJCNLP 2021 main conference, short paper
    47. [code]
  47. Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
    Jia-Chen Gu, Hui Liu, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu
    SIGIR 2021, full paper
    48. [code]
  48. Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
    Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu
    NAACL-HLT 2021, long paper
    49. [code]
  49. Have You Made A Decision? Where? A Pilot Study on Interpretability of Polarity Analysis Based on Advising Problem
    Tianda Li, Jia-Chen Gu, Hui Liu, Quan Liu, Zhen-hua Ling, Zhiming Su, Xiaodan Zhu
    ICASSP 2021, full paper
    50. [code]
  50. End-to-End Transition-Based Online Dialogue Disentanglement
    Hui Liu, Zhan Shi, Jia-Chen Gu, Quan Liu, Si Wei, Xiaodan Zhu
    IJCAI 2020, full paper
    51. [code]
  51. Towards Explainable NLP: A Generative Explanation Framework for Text Classification
    Hui Liu, Qingyu Yin, William Yang Wang
    ACL 2019, long paper
    52. [code]
  52. QuoteRec: Toward Quote Recommendation for Writing
    Jiwei Tan, Xiaojun Wan, Hui Liu, Jianguo Xiao
    ACM Transactions on Information Systems (TOIS), 2018

    53. Preprint

  53. Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
    Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He
    Manuscript, 2025

  54. Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
    Pengfei He, Yue Xing, Shen Dong, Juanhui Li, Zhenwei Dai, Xianfeng Tang, Hui Liu, Han Xu, Zhen Xiang, Charu C. Aggarwal, Hui Liu
    Manuscript, 2025

  55. Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents
    Jingying Zeng*, Hui Liu*, Zhenwei Dai*, Xianfeng Tang, Chen Luo, Samarth Varshney, Zhen Li, Qi He
    Manuscript, 2025

  56. How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities
    Minhua Lin, Hui Liu, Xianfeng Tang, Jingying Zeng, Zhenwei Dai, Chen Luo, Zheng Li, Xiang Zhang, Qi He, Suhang Wang
    Manuscript, 2025

  57. A Survey of Calibration Process for Black-Box LLMs
    Liangru Xie, Hui Liu, Jingying Zeng, Xianfeng Tang, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Qi He
    Manuscript, 2024

Projects

Miscellaneous

Image