PPaperPicks

Shumin Deng

24 papers at tracked venues · 17 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×9EMNLP ×5AAAI ×2NeurIPS ×2ICLR ×1ICML ×1NAACL ×1VLDB ×1WSDM ×1WWW ×1

Frequent coauthors

Mengru Wang
DBLP profile ↗ORCID search ↗
×3
Ziwen Xu
DBLP profile ↗ORCID search ↗
×2
Haoming Xu
DBLP profile ↗ORCID search ↗
×2
Yunzhi Yao
DBLP profile ↗ORCID search ↗
×2
Zekun Xi
DBLP profile ↗ORCID search ↗
×1
Kangwei Liu
DBLP profile ↗ORCID search ↗
×1
Buqiang Xu
DBLP profile ↗ORCID search ↗
×1
Lyucheng Wu
DBLP profile ↗ORCID search ↗
×1
Yedi Hu
DBLP profile ↗ORCID search ↗
×1
Yue Liu
DBLP profile ↗ORCID search ↗
×1
Yixin Ou
DBLP profile ↗ORCID search ↗
×1
Yuqi Zhu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
    ACL 2026 ·
    Ziwen Xu
    DBLP profile ↗ORCID search ↗
  2. Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
    ACL 2026 ·
    Haoming Xu
    DBLP profile ↗ORCID search ↗
  3. KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks
    AAAI 2026 ·
    Zekun Xi
    DBLP profile ↗ORCID search ↗
  4. LookAhead Tuning: Safer Language Models via Partial Answer Previews
    WSDM 2026 ·
    Kangwei Liu
    DBLP profile ↗ORCID search ↗
  5. StructMem: Structured Memory for Long-Horizon Behavior in LLMs
    ACL 2026 ·
    Buqiang Xu
    DBLP profile ↗ORCID search ↗
  6. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
    ACL 2026 ·
    Ziwen Xu
    DBLP profile ↗ORCID search ↗
  7. Automating Steering for Safe Multimodal Large Language Models
    EMNLP 2025 ·
    Lyucheng Wu
    DBLP profile ↗ORCID search ↗
  8. Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
    ACL 2025 ·
    Mengru Wang
    DBLP profile ↗ORCID search ↗
  9. CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
    EMNLP 2025 ·
    Yunzhi Yao
    DBLP profile ↗ORCID search ↗
  10. Exploring Model Kinship for Merging Large Language Models
    EMNLP 2025 ·
    Yedi Hu
    DBLP profile ↗ORCID search ↗
  11. FlipAttack: Jailbreak LLMs via Flipping
    ICML 2025 ·
    Yue Liu
    DBLP profile ↗ORCID search ↗
  12. How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
    ACL 2025 ·
    Yixin Ou
    DBLP profile ↗ORCID search ↗
  13. KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
    NAACL 2025 ·
    Yuqi Zhu
    DBLP profile ↗ORCID search ↗
  14. MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
    ICLR 2025 ·
    Chenxi Wang
    DBLP profile ↗ORCID search ↗
  15. PhishIntel: Toward Practical Deployment of Reference-Based Phishing Detection
    WWW 2025 ·
    Yuexin Li
    DBLP profile ↗ORCID search ↗
  16. ReLearn: Unlearning via Learning for Large Language Models
    ACL 2025 ·
    Haoming Xu
    DBLP profile ↗ORCID search ↗
  17. Agent Planning with World Knowledge Model
    NeurIPS 2024 ·
    Shuofei Qiao
    DBLP profile ↗ORCID search ↗
  18. Detoxifying Large Language Models via Knowledge Editing
    ACL 2024 ·
    Mengru Wang
    DBLP profile ↗ORCID search ↗
  19. Editing Conceptual Knowledge for Large Language Models
    EMNLP 2024 ·
    Xiaohan Wang
    DBLP profile ↗ORCID search ↗
  20. Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
    ACL 2024 ·
    Jintian Zhang
    DBLP profile ↗ORCID search ↗
  21. Knowledge Circuits in Pretrained Transformers
    NeurIPS 2024 ·
    Yunzhi Yao
    DBLP profile ↗ORCID search ↗
  22. Knowledge Mechanisms in Large Language Models: A Survey and Perspective
    EMNLP 2024 ·
    Mengru Wang
    DBLP profile ↗ORCID search ↗
  23. OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
    VLDB 2024 ·
    Ningyu Zhang
    DBLP profile ↗ORCID search ↗
  24. When Do Program-of-Thought Works for Reasoning?
    AAAI 2024 ·
    Zhen Bi
    DBLP profile ↗ORCID search ↗