Get started
Author

Zhiyu Xue

Observed name: Xue, Zhiyu
ORCID: 0009-0009-1389-0499
Observed ORCID: 0009-0009-1389-0499
OpenAlex ID: A5040852802
Detection of Mild Cognitive Impairment from Language Markers with Crossmodal Augmentation
2022 · Guangliang Liu, Zhiyu Xue, et al. · Pacific Symposium on Biocomputing (PSB) · 6
Group AdaBoost with Fairness Constraint
2023 · Zhiyu Xue · Society for Industrial and Applied Mathematics eBooks · 2
PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
2023 · Guangliang Liu, Zhiyu Xue, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Smaller Large Language Models Can Do Moral Self-Correction
2025 · Guangliang Liu, Zhiyu Xue, et al. · Workshop on Trustworthy NLP (TrustNLP) · 1
PDF
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
2024 · Liu, Guangliang, Mao, Haitao, et al. · arXiv (Cornell University) · 1
PDF
When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models
2026 · Fang, Yizhou, Chen, Siyue, et al. · arXiv (Cornell University)
PDF
Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
2026 · Che, Liwei, Xue, Zhiyu, et al. · arXiv (Cornell University)
PDF
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
2026 · Xue, Zhiyu, Qi, Zimo, et al. · arXiv (Cornell University)
PDF
Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection
2026 · Association for Computational Linguistics 2026, Abbasi-Asl, Reza, et al. · Underline Science Inc.
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
2026 · Association for Computational Linguistics 2026, Abbasi-Asl, Reza, et al. · Underline Science Inc.
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
2026 · Zhiyu Xue, Reza Abbasi-Asl, et al. · Conference of the European Chapter of the Association for Computational Linguistics
PDF
Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection
2026 · Zhiyu Xue, Reza Abbasi-Asl, et al. · Conference of the European Chapter of the Association for Computational Linguistics
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
2026 · Zhiyu Xue, Zimo Qi, et al. · Workshop on Trustworthy NLP (TrustNLP)
PDF
Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting
2026 · Liwei Che, Zhiyu Xue, et al. · Lecture notes in computer science
On the Convergence of Moral Self-Correction in Large Language Models
2025 · Association for Computational Linguistics 2025, Cao, Bochuan, et al. · Underline Science Inc.
On the Convergence of Moral Self-Correction in Large Language Models
2025 · Guangliang Liu, Haitao Mao, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)
PDF
No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
2024 · Xue, Zhiyu, Liu, Guangliang, et al. · arXiv (Cornell University)
PDF
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
2024 · Guangliang Liu, Milad Afshari, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Works count: 18
Citation count: 12
H-index: 2
I10-index:
Year
Topic
Type