May 23, 2023 · We propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group ...

Dec 6, 2023 · We reveal that these prompt optimization techniques are vulnerable to distribution shifts such as subpopulation shifts, which are com- mon for ...

We propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group ...

This work proposes Generalized Prompt Optimization framework, which incorporates the unlabeled data from the target group into prompt optimization, ...

View recent discussion. Abstract: Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks.

Feb 5, 2024 · We reveal the robustness issue of prompt opti- mization against distribution shifts and propose a new robust prompt optimization problem. • We ...

In this paper, we take an initial step of investigating the problem of LLM instruction optimization across data groups with distribution shifts. We find that ...

Missing: Distribution Shifts.

This is the official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks" by Andy Zhou, Bo Li, and Haohan ...

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide ...