A Causal Explainable Guardrails for Large Language Models

TL;DR

This paper introduces LLMGuardrail, a framework that uses causal analysis and adversarial learning to produce unbiased steering representations in large language models, improving their safety and alignment.

Contribution

It presents a novel method combining causal analysis and adversarial learning to mitigate biases in LLM steering representations, enhancing model safety and reliability.

Findings

Effective bias mitigation in LLM steering

Improved alignment with desired attributes

Enhanced explainability of model outputs

Abstract

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased representations and rely solely on steering prompts. However, the representations learned from pre-training can introduce semantic biases that influence the steering process, leading to suboptimal results. We propose LLMGuardrail, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations in LLMs. LLMGuardrail systematically identifies and blocks the confounding effects of biases, enabling the extraction of unbiased steering representations. Additionally, it includes an explainable component that provides insights into the alignment between the generated output and the desired direction. Experiments demonstrate LLMGuardrail's effectiveness in steering LLMs toward desired attributes while mitigating biases. Our work contributes to the development of safe and reliable LLMs that align with desired attributes.