Tai-Wei Chang
4 papers · 2014–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (11) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
AAAI (1)
COLING (1)
Top co-authors
Keywords
reinforcement learning from human feedback
(2)
reinforcement learning
(1)
probabilistic modeling
(1)
policy optimization
(1)
language model alignment
(1)
label noise
(1)
mirror descent
(1)
language model
(1)
reward model
(1)
credit assignment
(1)
causal graph
(1)
llm alignment
(1)
transition matrix
(1)
instance-dependent noise
(1)
large language model
(1)
reward redistribution
(1)
token-level reward
(1)
ai-generated feedback
(1)
reward composition
(1)
fairness theory
(1)
Papers
Learning Causal Transition Matrix for Instance-dependent Label Noise
AAAI 2025
RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
EMNLP 2025
Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
EMNLP 2024
Interpretation of Chinese Discourse Connectives for Explicit Discourse Relation Recognition
COLING 2014