Self-controller: Controlling LLMs with Multi-round Step-by-step Self-awareness

TL;DR

This paper introduces Self-controller, a novel framework that enhances LLMs' controllability by incorporating self-awareness and multi-round reasoning, improving efficiency and consistency across models.

Contribution

The work presents a new agentic framework for LLMs that enables self-awareness and step-by-step control, with theoretical analysis and practical algorithms for improved efficiency.

Findings

Demonstrates effective control over textual length in LLM outputs.

Introduces a binary search algorithm to accelerate generation.

Shows significant token savings with context caching technology.

Abstract

The applications of large language models (LLMs) have been widely spread across all domains. However, the basic abilities such as the controllability of LLMs are still limited. To address this, we propose "Self-controller", a novel agentic framework bringing self-awareness into LLMs' reasoning logic. The core idea of this work is to maintain states based on the LLM's response, letting the LLM become self-aware of current status and think step by step in a multi-round chain-of-thought paradigm. Our experiment on the state of textual length has shown the controllability and effectiveness of the Self-controller. We further implement a binary search algorithm to accelerate the generation process based on the linearity and monotonicity of the textual length state. Another advantage of the Self-controller comes with DeepSeek's Context Caching technology, which significantly saves computational token consumption when a cluster of conversations shares the same prefix of context. Theoretically, we prove that in this scenario the extra time complexity is $O(c \log n)$. Results of the back-of-the-envelope estimation suggest that the token consumption of our method is no more than twice as much as that of the trivial single-round generation. Furthermore, our ablation study on word constraints demonstrates the Self-controller's consistent controllability across all foundation models.