Mayi Xu

Venues

Frequent coauthors

Papers

1. ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
   WWW 2026 ·

   Hankun Kang

   DBLP profile ↗ORCID search ↗
2. Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
   AAAI 2026 ·

   Jiacheng Liu

   DBLP profile ↗ORCID search ↗
3. Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering
   AAAI 2026 ·

   Yunfeng Ning

   DBLP profile ↗ORCID search ↗
4. Recursive Short-to-Long Generalization for Multi-hop Reasoning
   SIGIR 2026 · Mayi Xu
5. A Survey on Training-free Alignment of Large Language Models
   EMNLP 2025 ·

   Birong Pan

   DBLP profile ↗ORCID search ↗
6. Aligning VLM Assistants with Personalized Situated Cognition
   ACL 2025 ·

   Yongqi Li

   DBLP profile ↗ORCID search ↗
7. CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
   ACL 2025 ·

   Xiaohu Li

   DBLP profile ↗ORCID search ↗
8. Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
   AAAI 2025 ·

   Yongqi Li

   DBLP profile ↗ORCID search ↗
9. Strong Empowered and Aligned Weak Mastered Annotation for Weak-to-Strong Generalization
   AAAI 2025 ·

   Yongqi Li

   DBLP profile ↗ORCID search ↗
10. Adaption-of-Thought: Learning Question Difficulty Improves Large Language Models for Reasoning
    EMNLP 2024 · Mayi Xu