Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO

TL;DR

This paper introduces CoIPO, a contrastive learning method that enhances LLM robustness against prompt noise by aligning logits from clean and noisy prompts, improving performance without external preprocessing.

Contribution

The paper proposes a novel intrinsic robustness training method for LLMs using contrastive learning on paired prompts, reducing reliance on external prompt refinement tools.

Findings

Significant accuracy improvements on NoisyPromptBench

Effective reduction of prompt sensitivity in LLMs

Outperforms existing robustness approaches

Abstract

Large language models (LLMs) have demonstrated remarkable and steadily improving performance across a wide range of tasks. However, LLM performance may be highly sensitive to prompt variations especially in scenarios with limited openness or strict output formatting requirements, indicating insufficient robustness. In real-world applications, user prompts provided to LLMs often contain imperfections, which may undermine the quality of the model's responses. To address this issue, previous work has primarily focused on preprocessing prompts, employing external tools or even LLMs to refine prompt formulations in advance. However, these approaches overlook the intrinsic robustness of LLMs, and their reliance on external components introduces additional computational overhead and uncertainty. In this work, we propose a Contrastive Learning-based Inverse Direct Preference Optimization (CoIPO) method that minimizes the discrepancy between the label-aligned logits produced by the model under a clean prompt and its noisy counterpart, and conduct a detailed analysis using mutual information theory. We augment the FLAN dataset by constructing paired prompts, each consisting of a clean prompt and its corresponding noisy version for training. Additionally, to evaluate the effectiveness, we develop NoisyPromptBench, a benchmark enhanced and derived from the existing PromptBench. Experimental results conducted on NoisyPromptBench demonstrate that our proposed method achieves a significant improvement in average accuracy over the current state-of-the-art approaches. The source code of CoIPO, pair-wise FLAN datasets, and NoisyPromptBench have already been released on https://github.com/vegetable-yx/CoIPO.