Chengzhengxu Li

Venues

Frequent coauthors

Papers

1. Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
   ACL 2026 · Chengzhengxu Li
2. Confidence Should Be Calibrated More Than One Turn Deep
   ACL 2026 ·

   Zhaohan Zhang

   DBLP profile ↗ORCID search ↗
3. MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
   AAAI 2026 ·

   Shengchao Liu

   DBLP profile ↗ORCID search ↗
4. Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training
   ACL 2025 ·

   Yuanfan Li

   DBLP profile ↗ORCID search ↗
5. Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
   NeurIPS 2024 · Chengzhengxu Li
6. Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning
   AAAI 2024 · Chengzhengxu Li
7. Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better
   ACL 2024 ·

   Shengchao Liu

   DBLP profile ↗ORCID search ↗
8. StablePT : Towards Stable Prompting for Few-shot Learning via Input Separation
   EMNLP 2024 ·

   Xiaoming Liu

   DBLP profile ↗ORCID search ↗