Saved in:
Bibliographic Details
Main Authors: Miyaoka, Yuya, Inoue, Masaki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.03121
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911551853690880
author Miyaoka, Yuya
Inoue, Masaki
author_facet Miyaoka, Yuya
Inoue, Masaki
contents This paper 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Control Barrier Function for Aligning Large Language Models
Miyaoka, Yuya
Inoue, Masaki
Computation and Language
Artificial Intelligence
Systems and Control
This paper 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.
title Control Barrier Function for Aligning Large Language Models
topic Computation and Language
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2511.03121