Xingyu Sui
6 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(2)
π
Cross-Pollinator
(12)
πΊοΈ
Taxonomy Completionist
(14)
Conferences
ACL (3)
EMNLP (2)
AAAI (1)
Top co-authors
Keywords
large language model
(4)
safety alignment
(2)
emotional support conversation
(2)
chain-of-thought reasoning
(1)
dialogue generation
(1)
model safety
(1)
ai safety
(1)
monte carlo tree search
(1)
preference modeling
(1)
adversarial defense
(1)
supervised fine-tuning
(1)
jailbreak attack
(1)
inference cost
(1)
jailbreak defense
(1)
strategy optimization
(1)
attack success rate
(1)
adaptive reasoning
(1)
activation steering
(1)
role-play fine-tuning
(1)
safety vulnerability
(1)
Papers
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
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
ACL 2026
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
ACL 2025
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
EMNLP 2025
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
EMNLP 2025