PPaperPicks

Haoran Li

Peking University, School of EECS, Beijing, China

27 papers at tracked venues · 14 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-1656-1278 ↗Homepage ↗

Venues

ACL ×12EMNLP ×9CIKM ×2AAAI ×1ECAI ×1NAACL ×1SIGKDD ×1

Frequent coauthors

Yulin Chen
DBLP profile ↗ORCID search ↗
×5
Wenbin Hu
DBLP profile ↗ORCID search ↗
×2
Chunkit Chan
DBLP profile ↗ORCID search ↗
×2
Jiecong Wang
DBLP profile ↗ORCID search ↗
×1
Changxuan Fan
DBLP profile ↗ORCID search ↗
×1
Ki Sen Hung
DBLP profile ↗ORCID search ↗
×1
Ying Su
DBLP profile ↗ORCID search ↗
×1
Yiyang Gu
DBLP profile ↗ORCID search ↗
×1
Cheng Jiayang
DBLP profile ↗ORCID search ↗
×1
Huihao Jing
DBLP profile ↗ORCID search ↗
×1
Weiqi Wang
DBLP profile ↗ORCID search ↗
×1
Zhiwei Yang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Activation-Guided Local Editing for Jailbreaking Attacks
    ACL 2026 ·
    Jiecong Wang
    DBLP profile ↗ORCID search ↗
  2. ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
    ACL 2026 · Haoran Li
  3. GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety
    ACL 2026 ·
    Changxuan Fan
    DBLP profile ↗ORCID search ↗
  4. Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
    ACL 2026 ·
    Ki Sen Hung
    DBLP profile ↗ORCID search ↗
  5. Jailbreaking Large Language Models with Morality Attacks
    ACL 2026 ·
    Ying Su
    DBLP profile ↗ORCID search ↗
  6. OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
    ACL 2026 ·
    Wenbin Hu
    DBLP profile ↗ORCID search ↗
  7. Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
    ACL 2026 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  8. SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models
    ACL 2026 ·
    Yiyang Gu
    DBLP profile ↗ORCID search ↗
  9. Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
    EMNLP 2025 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  10. Can Indirect Prompt Injection Attacks Be Detected and Removed?
    ACL 2025 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  11. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
    EMNLP 2025 ·
    Wenbin Hu
    DBLP profile ↗ORCID search ↗
  12. Defense Against Prompt Injection Attack by Leveraging Attack Techniques
    ACL 2025 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  13. InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding
    EMNLP 2025 ·
    Cheng Jiayang
    DBLP profile ↗ORCID search ↗
  14. MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
    EMNLP 2025 ·
    Huihao Jing
    DBLP profile ↗ORCID search ↗
  15. On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
    EMNLP 2025 ·
    Weiqi Wang
    DBLP profile ↗ORCID search ↗
  16. PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
    ACL 2025 · Haoran Li
  17. Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory
    NAACL 2025 · Haoran Li
  18. Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
    AAAI 2025 · Haoran Li
  19. TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
    EMNLP 2025 ·
    Yulin Chen
    DBLP profile ↗ORCID search ↗
  20. Adaptive Differentially Private Structural Entropy Minimization for Unsupervised Social Event Detection
    CIKM 2024 ·
    Zhiwei Yang
    DBLP profile ↗ORCID search ↗
  21. Audience Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
    ECAI 2024 ·
    Chunkit Chan
    DBLP profile ↗ORCID search ↗
  22. GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
    EMNLP 2024 ·
    Wei Fan
    DBLP profile ↗ORCID search ↗
  23. LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
    EMNLP 2024 ·
    Jiangshu Du
    DBLP profile ↗ORCID search ↗
  24. NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding
    EMNLP 2024 ·
    Chunkit Chan
    DBLP profile ↗ORCID search ↗
  25. PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
    ACL 2024 · Haoran Li
  26. Privacy-Preserved Neural Graph Databases
    SIGKDD 2024 ·
    Qi Hu
    DBLP profile ↗ORCID search ↗
  27. Table-Filling via Mean Teacher for Cross-domain Aspect Sentiment Triplet Extraction
    CIKM 2024 ·
    Kun Peng
    DBLP profile ↗ORCID search ↗