Zhexin Zhang
19 papers · 2021–2026 · 4 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (37) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(11)
🤝
Dynamic Duo
(18)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(102)
Top co-authors
Research topics
Artificial Intelligence
(15)
Natural Language Processing
(15)
Core AI
(15)
Deep Learning
(8)
Machine Learning
(8)
Generation
(7)
Learning Types · Machine Learning
(6)
Resources & Methods
(6)
Applications
(5)
Learning Types · Deep Learning
(5)
Application Areas
(3)
Security & Privacy
(2)
Privacy
(2)
Techniques
(2)
Knowledge & Reasoning
(1)
Keywords
large language model
(6)
natural language generation
(3)
safety evaluation
(3)
text generation
(3)
safety detection
(2)
text classification
(2)
adversarial attack
(2)
dialogue system
(2)
attack success rate
(2)
story generation
(2)
language model
(2)
explainable ai
(2)
safety alignment
(2)
jailbreaking attack
(2)
dialogue generation
(1)
adversarial robustness
(1)
conversational ai
(1)
text editing
(1)
multi-task learning
(1)
zero-shot learning
(1)
Papers
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
ACL 2026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
ACL 2026
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
ACL 2026
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity
AAAI 2026
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
ACL 2025
LongSafety: Evaluating Long-Context Safety of Large Language Models
ACL 2025
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
ACL 2024
SafetyBench: Evaluating the Safety of Large Language Models
ACL 2024
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
EMNLP 2024
ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
ACL 2023
InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning
EMNLP 2023
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
ACL 2023
Self-Supervised Sentence Polishing by Adding Engaging Modifiers
ACL 2023
Unveiling the Implicit Toxicity in Large Language Models
EMNLP 2023
Automatic Comment Generation for Chinese Student Narrative Essays
EMNLP 2022
Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
EMNLP 2022
Persona-Guided Planning for Controlling the Protagonist’s Persona in Story Generation
NAACL 2022
Selecting Stickers in Open-Domain Dialogue through Multitask Learning
ACL 2022
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics
ACL 2021