Papers by Haomin Zhuang

5 papers
Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used to remove harmful knowledge and undesirable capabilities.
Approach: They propose a framework that leverages Cognitive Diagnosis Modeling to evaluate LLM unlearning.
Outcome: The proposed framework enhances evaluation and facilitates removal of harmful abilities.
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Copied to clipboard

Challenge: prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach: They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome: The proposed model maintains safety while reducing over-refusal.
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in LLMs unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model’s utility for legitimate knowledge.
Approach: They propose a Selected-Expert Unlearning Framework (SEUF) that combines expert attribution and an anchor loss to ensure controlled unlearning.
Outcome: Experiments show that the proposed framework improves forget quality and model utility by 35% on MoE LLMs across benchmarks and LLM architectures compared to standard unlearning algorithms .
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process.
Approach: They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Outcome: The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Defending Jailbreak Prompts via In-Context Adversarial Game (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications, but concerns regarding their security persist.
Approach: They propose an adversarial game that leverages agent learning to extend knowledge to defend against jailbreaks.
Outcome: The proposed game shows that LLMs safeguarded by ICAG exhibit significantly reduced jailbreak success rates across various attack scenarios.

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