Papers by Zenghao Duan

5 papers
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content.
Approach: They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces .
Outcome: The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining.
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject (2025.naacl-short)

Copied to clipboard

Challenge: Existing knowledge editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject.
Approach: They propose a benchmark to assess the effectiveness of knowledge editing methods . they use same-subject edits to ensure comprehensive updates to entity-centric knowledge .
Outcome: The proposed method over-relys on subject information, neglecting other critical factors, resulting in reduced editing effectiveness.
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Copied to clipboard

Challenge: Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach: They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome: The proposed method reduces token usage by up to 44% while preserving accuracy.
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks.
Approach: They propose a framework that exploits AdVersArial meTAphoR to induce LLMs to calibrate harmful metaphors for jailbreaking.
Outcome: The proposed framework can successfully jailbreak Large Language Models (LLMs) by leveraging the AdVersArial meTAphoR (AVATAR) framework achieves state-of-the-art attack success rate across multiple advanced LLMs.
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models have been developed to deal with real-world crimes, but it remains unclear whether they internalize authentic knowledge or are forced to simulate toxic language patterns.
Approach: They construct knowledge-intensive Q&A to investigate misuse threats of Large Language Models in terms of dangerous knowledge possession, harmful task planning utility, and harmfulness judgment robustness.
Outcome: The findings raise concerns that jailbreak success is often attributable to a hallucination loop between jailbroken LLM and judger LLM .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations