Chengzhengxu Li
8 papers · 2024–2026 · 4 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 · Silver
🗺️
Taxonomy Completionist
(29)
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Natural Language Processing
(7)
Learning Types · Machine Learning
(6)
Artificial Intelligence
(5)
Deep Learning
(5)
Learning Types · Deep Learning
(5)
Core AI
(4)
Applications
(3)
Learning Paradigms
(3)
Resources & Methods
(3)
Application Areas
(2)
Generation
(2)
Reinforcement Learning
(1)
Methods
(1)
Models
(1)
Keywords
large language model
(3)
machine-generated text detection
(3)
domain generalization
(2)
text classification
(2)
contrastive learning
(2)
few-shot learning
(2)
prompt optimization
(2)
pre-trained language model
(2)
soft prompt
(2)
policy gradient
(1)
confidence calibration
(1)
adversarial training
(1)
greedy search
(1)
adversarial attack
(1)
frequency domain
(1)
input separation
(1)
multi-turn calibration
(1)
post-reasoning paradigm
(1)
hard prompt
(1)
decoding strategy
(1)
Papers
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
ACL 2026
Confidence Should Be Calibrated More Than One Turn Deep
ACL 2026
MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
AAAI 2026
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training
ACL 2025
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
NeurIPS 2024
Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning
AAAI 2024
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better
ACL 2024
StablePT : Towards Stable Prompting for Few-shot Learning via Input Separation
EMNLP 2024