SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.15625 · 2024

CBF-LLM: Safe Control for LLM Alignment

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 safety filter, designed based on the CBF, to the output generation of the baseline LLM, i.e., the sequence of the token, with the aim of intervening in the generated text. The overall text-generation system is implemented with Llama 3 and a RoBERTa model, and the source code is available at https://github.com/Mya-Mya/CBF-LLM. The experiment demonstrates its control ability and effectiveness in reducing the number of interventions needed for user-specified alignment tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.15625")
get_code_for_paper("2408.15625")
have("2408.15625")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.15625.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.15625.svg)](https://syntology.ai/paper/2408.15625)

Connect an agent — have() is free.