Zengzhi Wang

5 papers · 2024–2025 · 3 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 (12) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ACL (2) NeurIPS (2) ICML (1)

Top co-authors

Pengfei Liu (4) Run-Ze Fan (2) Xuefeng Li (2) Fan Zhou (2) Rui Xia (2) Ruijie Xu (2) Steffi Chern (1) Shaoting Zhang (1) Yixin Ye (1) Zhen Huang (1)

Research topics

Machine Learning (4) Natural Language Processing (4) Resources & Methods (4) Artificial Intelligence (3) Core AI (3) Application Areas (2) Learning Types (2) Deep Learning (1) Models (1)

Keywords

large language model (3) pretraining corpus (2) data contamination (2) foundation model (1) evaluation benchmark (1) data quality (1) continual pre-training (1) prompting strategy (1) multimodal model (1) scientific discovery (1) preference data (1) cognitive reasoning (1) evaluation dataset (1) prompting strategies (1) judgment consistency (1) follow-up questioning (1) data refinement (1) preference data synthesis (1) training-based framework (1) fine-grained operations (1)

Papers

Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale ICML 2025 Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment ACL 2024 Data Contamination Report from the 2024 CONDA Shared Task ACL 2024 MathPile: A Billion-Token-Scale Pretraining Corpus for Math NeurIPS 2024 OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI NeurIPS 2024