Zimo Qi
4 papers · 2025–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(8)
Conferences
EMNLP (2)
AACL (1)
IJCNLP (1)
Keywords
moral self-correction
(2)
moral reasoning
(2)
generalization ability
(1)
distributional semantics
(1)
behavioral analysis
(1)
learning paradigm
(1)
large language model
(1)
moral alignment
(1)
mechanistic analysis
(1)
external feedback
(1)
pragmatic dilemma
(1)
discourse heuristic
(1)
output alignment
(1)
self-diagnosis capability
(1)
ethical judgment
(1)
situational generalization
(1)
responsible ai
(1)
Papers
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
EMNLP 2025
Discourse Heuristics For Paradoxically Moral Self-Correction
EMNLP 2025
Moral Self-correction is Not An Innate Capability in Language Models
IJCNLP 2025
Moral Self-correction is Not An Innate Capability in Language Models
AACL 2025