Xinghua Zhang
10 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (30) 🐣 Hot Topic Early Bird 🗃️ Keyword Collector (64)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(8)
Natural Language Processing
(7)
Machine Learning
(6)
Learning Types
(6)
Resources & Methods
(5)
Deep Learning
(4)
Data Science & Analytics
(2)
Application Areas
(2)
Applications · Data Science & Analytics
(2)
Models
(2)
Optimization & Theory
(2)
Applications · Natural Language Processing
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
large language model
(6)
instruction following
(2)
complex instruction
(2)
benchmark evaluation
(2)
dialogue generation
(1)
transfer learning
(1)
policy optimization
(1)
knowledge editing
(1)
imitation learning
(1)
model evaluation
(1)
knowledge transfer
(1)
named entity recognition
(1)
preference optimization
(1)
language model evaluation
(1)
privacy preservation
(1)
direct preference optimization
(1)
safety alignment
(1)
error detection
(1)
model alignment
(1)
multi-task learning
(1)
Papers
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
ACL 2025
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
EMNLP 2025
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
ACL 2025
On the Role of Attention Heads in Large Language Model Safety
ICLR 2025
Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing
EMNLP 2025
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
EMNLP 2024
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
EMNLP 2024
Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation
AAAI 2023
Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation
IJCAI 2021
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning
EMNLP 2021