Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from SIGIR 2026 / reviewers in the wild / expert

Zenghao Duan

dblp:399/8169 · DBLP profile ↗
← Back
3ranked-venue papers
1as first author
3since 2021 · last 2026
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 3 · 1 first-author · 3 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
3 papers
Language models and text generation · 50% Trustworthy machine learning · 28% Representation and self-supervised learning · 22%
Network and information security
1 paper
Security and privacy of machine learning · 100%

Topics — the 7 heaviest of 9, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Language models and text generation › large language model safety
detoxification		 1.012026
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification · ACL (1) 2026
Natural language and speech › Language models and text generation › large language model reasoning
overthinking		 1.012026
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis · ACL (1) 2026
Machine learning › Trustworthy machine learning
robustness		 1.012026
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification · ACL (1) 2026
Machine learning › Representation and self-supervised learning › representation learning › dimensionality reduction › subspace learning
subspace projection		 1.012026
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification · ACL (1) 2026
Security and privacy of machine learning › adversarial attack
jailbreak attack		 0.912025
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors · ACL (1) 2025
Natural language and speech › Language models and text generation
chain-of-thought reasoning		 0.312026
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis · ACL (1) 2026
Machine learning › Trustworthy machine learning › adversarial machine learning › adversarial natural language processing
prompt-based attack		 0.312025
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors · ACL (1) 2025

Methods — techniques the papers use, named apart from their topics

adversarial metaphor generation · 1.7subspace projection · 1.0reasoning dynamics analysis · 1.0
YearPublicationVenuePosition
2026 Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
abstract
Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Zenghao Duan, Zhiyi Yin, Zhichao Shi 0001, Liang Pang 0001, Shaoling Jing, Zihe Huang, Jingcheng Deng, Huawei Shen, Xueqi Cheng 0001
 ACL (1)1
2026 The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
abstract
Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Zihao Wei, Liang Pang 0001, Wenjie Shi, Jingcheng Deng, Zenghao Duan, Jingang Wang, Fei Sun 0001, Huawei Shen, Xueqi Cheng 0001
 ACL (1)7
2025 from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
abstract
Yu Yan, Sheng Sun, Zenghao Duan, Teli Liu, Min Liu, Zhiyi Yin, LeiJingyu LeiJingyu, Qi Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Zenghao Duan, Teli Liu, Zhiyi Yin, LeiJingyu LeiJingyu
 ACL (1)3