When control meets large language models: From words to dynamics
Komeil Nosrati, Aleksei Tepljakov, Juri Belikov, Eduard Petlenkov

TL;DR
This paper explores the intersection of large language models and control theory, proposing a bidirectional framework that enhances control design and alignment through dynamic system perspectives.
Contribution
It introduces a novel continuum connecting prompt engineering and system dynamics, advancing control applications and interpretability of LLMs.
Findings
LLMs can assist in controller design and research workflows.
Control concepts improve LLM alignment and safety.
Treating LLMs as dynamic systems enables new control strategies.
Abstract
While large language models (LLMs) are transforming engineering and technology through enhanced control capabilities and decision support, they are simultaneously evolving into complex dynamical systems whose behavior must be regulated. This duality highlights a reciprocal connection in which prompts support control system design while control theory helps shape prompts to achieve specific goals efficiently. In this study, we frame this emerging interconnection of LLM and control as a bidirectional continuum, from prompt design to system dynamics. First, we investigate how LLMs can advance the field of control in two distinct capacities: directly, by assisting in the design and synthesis of controllers, and indirectly, by augmenting research workflows. Second, we examine how control concepts help LLMs steer their trajectories away from undesired meanings, improving reachability and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Neurobiology of Language and Bilingualism · Natural Language Processing Techniques
