Qianxi He
4 papers · 2024–2025 · 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.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Natural Language Processing
(3)
Learning Types · Deep Learning
(3)
Resources & Methods
(3)
Machine Learning
(2)
Core Methods
(2)
Application Areas
(1)
Applications
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Keywords
large language model
(3)
instruction following
(2)
complex instruction
(2)
reward modeling
(1)
logical reasoning
(1)
data augmentation
(1)
chain-of-thought reasoning
(1)
natural language understanding
(1)
model training
(1)
directed acyclic graph
(1)
confidence estimation
(1)
instruction understanding
(1)
reasoning generalization
(1)
order-centric augmentation
(1)
premise ordering
(1)
confidence-aware reasoning
(1)
ppo training
(1)
reasoning capabilities
(1)
reasoning performance
(1)
reasoning order
(1)
Papers
Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
EMNLP 2025
Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
EMNLP 2025
Can Large Language Models Understand Real-World Complex Instructions?
AAAI 2024
From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
EMNLP 2024