4 papers
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…
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…
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…
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…