Yulin Hu
9 papers · 2024–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(7)
Learning Types · Machine Learning
(6)
Natural Language Processing
(5)
Resources & Methods
(3)
Generation
(2)
Optimization & Theory
(2)
Deep Learning
(1)
Interdisciplinary
(1)
Application Areas
(1)
Applications
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Social
(1)
Keywords
large language model
(7)
safety alignment
(3)
preference learning
(2)
catastrophic forgetting
(2)
emotional support conversation
(2)
knowledge transfer
(1)
direct preference optimization
(1)
adversarial learning
(1)
ai safety
(1)
inference cost
(1)
instruction tuning
(1)
model safety
(1)
monte carlo tree search
(1)
preference modeling
(1)
parameter-efficient tuning
(1)
dialogue generation
(1)
supervised fine-tuning
(1)
jailbreak attack
(1)
adversarial defense
(1)
chain-of-thought reasoning
(1)
Papers
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
ACL 2026
Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
AAAI 2026
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
ACL 2026
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
EMNLP 2025
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
ACL 2025
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
EMNLP 2025
MPO: Multilingual Safety Alignment via Reward Gap Optimization
ACL 2025
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
ACL 2024
SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
ACL 2024