activity
20232025
most citedMulti-task Prompt Words Learning for Social Media Content Generation

1 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CL2025

Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization

Chong Zhang, Xiang Li, Jia Wang +3

LLMs increasingly integrate auto-suggestion optimization modules, enabling them to rewrite and display user input before generating the final response. While this design aims to en…

cs.CL20241 cited

Multi-task Prompt Words Learning for Social Media Content Generation

Haochen Xue, Chong Zhang, Chengzhi Liu +2

The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. Howeve…

cs.CL20241 cited

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities

Wenyue Hua, Kaijie Zhu, Lingyao Li +7

This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from…

q-bio.BM2024

ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction

Mingyu Jin, Haochen Xue, Zhenting Wang +5

The prediction of protein-protein interactions (PPIs) is crucial for understanding biological functions and diseases. Previous machine learning approaches to PPI prediction mainly…

cs.CR2024

Goal-guided Generative Prompt Injection Attack on Large Language Models

Chong Zhang, Mingyu Jin, Qinkai Yu +3

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or…

cs.CV2023

Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning

Chong Zhang, Mingyu Jin, Qinkai Yu +3

Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training. However, GZSL methods are prone to bia…