Yulin Chen

Venues

Frequent coauthors

Papers

1. Causal Discovery as Dialectical Aggregation: A Quantitative Argumentation Framework
   KR 2026 ·

   Sheng Wei

   DBLP profile ↗ORCID search ↗
2. ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
   ACL 2026 ·

   Haoran Li

   DBLP profile ↗ORCID search ↗
3. EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics
   ACL 2026 ·

   Zhichen Tang

   DBLP profile ↗ORCID search ↗
4. Learning on Imbalanced Noisy Data via Debiased Sample Selection and LLM-Driven Annotation
   ACL 2026 ·

   Bo Yuan

   DBLP profile ↗ORCID search ↗
5. Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
   ACL 2026 ·

   Yuan Sui

   DBLP profile ↗ORCID search ↗
6. One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
   AAAI 2026 ·

   Zeyuan Wang

   DBLP profile ↗ORCID search ↗
7. Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
   ACL 2026 · Yulin Chen
8. Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots through LLM-Generated Probes
   CHI 2026 ·

   John Driscoll

   DBLP profile ↗ORCID search ↗
9. Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
   EMNLP 2025 · Yulin Chen
10. Can Indirect Prompt Injection Attacks Be Detected and Removed?
    ACL 2025 · Yulin Chen
11. Defense Against Prompt Injection Attack by Leveraging Attack Techniques
    ACL 2025 · Yulin Chen
12. Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
    EMNLP 2025 ·

    Yufei He

    DBLP profile ↗ORCID search ↗
13. GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
    NeurIPS 2025 ·

    Yue Liu

    DBLP profile ↗ORCID search ↗
14. PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
    ACL 2025 ·

    Haoran Li

    DBLP profile ↗ORCID search ↗
15. Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory
    NAACL 2025 ·

    Haoran Li

    DBLP profile ↗ORCID search ↗
16. Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
    AAAI 2025 ·

    Haoran Li

    DBLP profile ↗ORCID search ↗
17. TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
    EMNLP 2025 · Yulin Chen
18. Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning
    ACL 2025 ·

    Bo Yuan

    DBLP profile ↗ORCID search ↗
19. Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLMs-Powered Assistance
    ACL 2024 ·

    Bo Yuan

    DBLP profile ↗ORCID search ↗
20. Label Distribution Learning-Enhanced Dual-KNN for Text Classification
    SDM 2024 ·

    Bo Yuan

    DBLP profile ↗ORCID search ↗