Shitong Duan
6 papers · 2024–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π§
Keyword Pioneer
π
Cross-Pollinator
(13)
Conferences
AAAI (2)
ACL (1)
EMNLP (1)
ICLR (1)
IJCAI (1)
Top co-authors
Keywords
large language model
(2)
visual question answering
(1)
preference learning
(1)
preference optimization
(1)
language model alignment
(1)
responsible ai
(1)
model alignment
(1)
benchmark dataset
(1)
multimodal large language model
(1)
scalable oversight
(1)
value alignment
(1)
value evaluation
(1)
human preference
(1)
personality trait
(1)
ai alignment
(1)
negative sample
(1)
unanswerable question
(1)
ethical ai
(1)
personality modeling
(1)
trustworthiness evaluation
(1)
Papers
MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
AAAI 2026
IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
AAAI 2026
Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMsβ Value Evaluation
ACL 2025
Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
EMNLP 2024
DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
ICLR 2024
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
IJCAI 2024