Jiaojiao Jiang
3 papers · 2026–2026 · 2 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.
Top co-authors
Research topics
Keywords
detoxification
(2)
policy optimization
(1)
language model
(1)
identity preserving
(1)
hate speech
(1)
counter speech
(1)
masked diffusion
(1)
edit chain
(1)
representations
(1)
stance
(1)
domain
(1)
contrastive
(1)
selective-guidance
(1)
multiplicative reward
(1)
structured editing
(1)
causal inference
(1)
veto-aligned
(1)
Papers
Identity-Preserving Detoxification via Local Causal Effect Ranking on Masked Diffusion Language Models
EMNLP 2026
Learning What Is Said, Not How: Stance-Contrastive Learning for Generalizable Hate Speech Detection
AACL 2026
STEER: Structured Text Editing via Edit-Chain Reinforcement Learning
EMNLP 2026