Control Barrier Function for Aligning Large Language Models

Yuya Miyaoka

doi:10.1109/TCST.2026.3675329

Control Barrier Function for Aligning Large Language Models

2026-03-27

0

PRE

AI

DOI：10.1109/TCST.2026.3675329

Original

Original request for help

Save

Abstract

En 中文

This article proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the CBF safety filter to the predicted token generated from the baseline LLM to intervene in the generated text. The safety filter includes two significant advantages: this safety filter is an add-on type, allowing it to be used for alignment purposes without fine-tuning the baseline LLM, and if there is an evaluation model regarding the desired alignment, it can be directly applied to the filter design. The overall text-generation system is implemented with open-source language models, aiming to generate positive text.

Keywords:

Alignment

control barrier function (CBF)

large language models (LLMs)

safe control

Control Barrier Function for Aligning Large Language Models

Abstract

Journal

Organization

Cited Papers