Shiqi Gao
5 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (23) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
β
The Questioner
Conferences
AAAI (2)
NIPS (2)
ACL (1)
Top co-authors
Research topics
Keywords
large language model
(3)
feature alignment
(1)
representation learning
(1)
anomaly detection
(1)
question answering
(1)
confidence calibration
(1)
prior knowledge
(1)
monte carlo sampling
(1)
secure aggregation
(1)
poisoning attack
(1)
parameter-efficient fine-tuning
(1)
uncertainty estimation
(1)
fully homomorphic encryption
(1)
privacy protection
(1)
poisoning attack mitigation
(1)
knowledge boundary
(1)
calibration error
(1)
trustworthy ai
(1)
expected calibration error
(1)
homomorphic encryption
(1)
Papers
Fine-Tuned LLMs Know They Donβt Know: A Parameter-Efficient Approach to Recovering Honesty
AAAI 2026
FLUE: Streamlined Uncertainty Estimation for Large Language Models
AAAI 2025
Towards Objective Fine-tuning: How LLMsβ Prior Knowledge Causes Potential Poor Calibration?
ACL 2025
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
NIPS 2024
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
NIPS 2024