Hui Liu

Venues

Frequent coauthors

Papers

1. A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning
   ACL 2026 ·

   Yingqian Cui

   DBLP profile ↗ORCID search ↗
2. Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization
   ACL 2026 ·

   Yu Fu

   DBLP profile ↗ORCID search ↗
3. Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
   ACL 2026 ·

   Zhining Liu

   DBLP profile ↗ORCID search ↗
4. Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
   AAAI 2026 ·

   Yu Fu

   DBLP profile ↗ORCID search ↗
5. A General Framework to Enhance Fine-tuning-based LLM Unlearning
   ACL 2025 ·

   Jie Ren

   DBLP profile ↗ORCID search ↗
6. A Survey on Small Language Models in the Era of Large Language Models: Architecture, Capabilities, and Trustworthiness
   SIGKDD 2025 ·

   Fali Wang

   DBLP profile ↗ORCID search ↗
7. AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
   NeurIPS 2025 ·

   Fali Wang

   DBLP profile ↗ORCID search ↗
8. Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
   EMNLP 2025 ·

   Jiankun Zhang

   DBLP profile ↗ORCID search ↗
9. Catastrophic Failure of LLM Unlearning via Quantization
   ICLR 2025 ·

   Zhiwei Zhang

   DBLP profile ↗ORCID search ↗
10. Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions?
    ACL 2025 ·

    Xianren Zhang

    DBLP profile ↗ORCID search ↗
11. EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
    ACL 2025 ·

    Weiqi Wang

    DBLP profile ↗ORCID search ↗
12. Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
    SIGIR 2025 ·

    Jingying Zeng

    DBLP profile ↗ORCID search ↗
13. Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data
    NAACL 2025 ·

    Juanhui Li

    DBLP profile ↗ORCID search ↗
14. Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
    ICML 2025 ·

    Tianci Liu

    DBLP profile ↗ORCID search ↗
15. SUA: Stealthy Multimodal Large Language Model Unlearning Attack
    EMNLP 2025 ·

    Xianren Zhang

    DBLP profile ↗ORCID search ↗
16. SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
    NAACL 2025 ·

    Ran Xu

    DBLP profile ↗ORCID search ↗
17. Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
    NAACL 2025 ·

    Shenglai Zeng

    DBLP profile ↗ORCID search ↗
18. Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
    ICLR 2025 ·

    Tianci Liu

    DBLP profile ↗ORCID search ↗
19. ViLBench: A Suite for Vision-Language Process Reward Modeling
    EMNLP 2025 ·

    Haoqin Tu

    DBLP profile ↗ORCID search ↗