Control Barrier Function for Aligning Large Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
CBF-LLM: Safe Control for LLM Alignment
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 …
Text GenerationControl Barrier Corridors: From Safety Functions to Safe Sets
Safe autonomy is a critical requirement and a key enabler for robots to operate safely in unstructured complex environments. Control barrier functions and safe motion corridors are two widely used but technically distinc…
Motion PlanningLearning Robust Hybrid Control Barrier Functions for Uncertain Systems
The need for robust control laws is especially important in safety-critical applications. We propose robust hybrid control barrier functions as a means to synthesize control laws that ensure robust safety. Based on this …
Safety Control of Uncertain MIMO Systems Using Dynamic Output Feedback Barrier Pairs
Safety control of dynamical systems using barrier functions relies on knowing the full state information. This paper introduces a novel approach for safety control in uncertain MIMO systems with partial state information…
BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems
Safety verification of dynamical systems via barrier certificates is essential for ensuring correctness in autonomous applications. Synthesizing these certificates involves discovering mathematical functions with current…