Zhichao Shi

Orcid: 0009-0006-7835-7984

Affiliations:
  • Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China


According to our database1, Zhichao Shi authored at least 10 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis.
CoRR, May, 2026

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
JudgeAgent: Knowledge-wise and Dynamic LLM Evaluation with Agent-as-Interviewer.
CoRR, September, 2025

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace.
CoRR, May, 2025

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models.
Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, 2025

SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

2024
A Survey on LLM-as-a-Judge.
CoRR, 2024

Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets.
Proceedings of the ACM on Web Conference 2024, 2024

MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Unlocking the Power of Large Language Models for Entity Alignment.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024


  Loading...