ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making

TL;DR

ALIGN introduces a prompt-based system for dynamically personalizing large language models to align with user-specific attributes, enhancing decision-making reliability and responsibility.

Contribution

It presents a novel, flexible framework for attribute alignment and personalization of LLMs, with a modular design and open-source implementation.

Findings

Effective attribute alignment in public opinion and medical domains

Flexible system with swappable LLM backbones

Enables qualitative and quantitative analysis of LLM alignment

Abstract

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization. Existing LLM comparison tools largely focus on benchmarking tasks, such as knowledge-based question answering. In contrast, our proposed ALIGN system focuses on dynamic personalization of LLM-based decision-makers through prompt-based alignment to a set of fine-grained attributes. Key features of our system include robust configuration management, structured output generation with reasoning, and several algorithm implementations with swappable LLM backbones, enabling different types of analyses. Our user interface enables a qualitative, side-by-side comparison of LLMs and their alignment to various attributes, with a modular backend for easy algorithm integration. Additionally, we perform a quantitative analysis comparing alignment approaches in two different domains: demographic alignment for public opinion surveys and value alignment for medical triage decision-making. The entire ALIGN framework is open source and will enable new research on reliable, responsible, and personalized LLM-based decision-makers.