Taiwei Shi
7 papers · 2023–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π Conference Polyglot (2) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
(2)
Conferences
EMNLP (4)
NAACL (2)
ACL (1)
Top co-authors
Keywords
large language model
(4)
uncertainty estimation
(2)
language model
(2)
instruction tuning
(2)
preference alignment
(1)
data annotation
(1)
toxicity detection
(1)
language model alignment
(1)
reinforcement learning from human feedback
(1)
human-ai collaboration
(1)
user feedback
(1)
alignment evaluation
(1)
hallucination detection
(1)
refusal behavior
(1)
human-ai interaction
(1)
online discourse
(1)
unanswerable question
(1)
conversation datum
(1)
ideological bia
(1)
community norm
(1)
Papers
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
ACL 2026
STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models
EMNLP 2025
The Hallucination Tax of Reinforcement Finetuning
EMNLP 2025
Can Language Model Moderators Improve the Health of Online Discourse?
NAACL 2024
Safer-Instruct: Aligning Language Models with Automated Preference Data
NAACL 2024
How Susceptible are Large Language Models to Ideological Manipulation?
EMNLP 2024
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
EMNLP 2023