Peixuan Han
4 papers · 2025–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(2)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (3)
ACL (1)
Top co-authors
Keywords
large language model
(2)
decision making
(1)
symbolic reasoning
(1)
puzzle solving
(1)
chain-of-thought reasoning
(1)
working memory
(1)
ai safety
(1)
language model
(1)
language model agent
(1)
tool use
(1)
utility function
(1)
harmful content detection
(1)
scientific discovery
(1)
decision support
(1)
llm agent
(1)
internal activation
(1)
creative reasoning
(1)
explainable reasoning
(1)
trade-off evaluation
(1)
risk-aware evaluation
(1)
Papers
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents
ACL 2025
SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery
EMNLP 2025
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
EMNLP 2025
DecisionFlow: Advancing Large Language Model as Principled Decision Maker
EMNLP 2025