Papers by Longzhu He
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing defenses against jailbreaks focus on perturbing or inspecting inputs, but ignore competing objectives, the underlying cause of alignment failures. |
| Approach: | They propose a novel defense that employs adaptive decoding to address the root causes of jailbreak issues. |
| Outcome: | The proposed defense improves safety alignment while maintaining helpfulness. |
Beyond the Textual: Generating Coherent Visual Options for MCQs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multiple choice questions (MCQs) are crucial for deep thinking and knowledge integration in education. |
| Approach: | They propose a cross-modal options synthesis framework for generating MCQs with visual options. |
| Outcome: | The proposed framework produces a plausible and visually similar answer and distractor . it also includes a discrimination module to identify content suitable for visual options . |
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting (2026.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on structured fact triples, overlooking diverse unstructured forms of factual information. |
| Approach: | They propose a method that allows LLMs to edit knowledge via **Chain of Thoughts** reasoning. |
| Outcome: | The proposed method achieves strong generalization across six diverse knowledge editing scenarios with a single round of training on three open-source language models. |