collaborators

8 papers

cs.CL2025

Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient

Zeru Shi, Zhenting Wang, Yongye Su +5

While automatic prompt generation methods have recently received significant attention, their robustness remains poorly understood. In this paper, we introduce PertBench, a compreh…

cs.CL2025

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs

Rui Wu, Yihao Quan, Zeru Shi +3

Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs that contain sensitive surface si…

cs.LG2025

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning

Zeru Shi, Yingjia Wan, Zhenting Wang +4

Motivated by the puzzling observation that inserting long sequences of meaningless tokens before the query prompt can consistently enhance LLM reasoning performance, this work anal…

cs.CL2025

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System

Qinkai Yu, Mingyu Jin, Dong Shu +8

Recent advancements in artificial intelligence (AI), especially large language models (LLMs), have significantly advanced healthcare applications and demonstrated potentials in int…

cs.CL2025

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs

Sam Lin, Wenyue Hua, Zhenting Wang +3

Cloud-based Large Language Models (LLMs) such as ChatGPT have become increasingly integral to daily operations. Nevertheless, they also introduce privacy concerns: firstly, numerou…

cs.LG2025

ADO: Automatic Data Optimization for Inputs in LLM Prompts

Sam Lin, Wenyue Hua, Lingyao Li +2

This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts. While previous research has p…