Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models

TL;DR

This paper introduces a lightweight, adaptive framework for multi-aspect controllable text generation with large language models, addressing limitations of existing methods by dynamically adjusting parameters for better control and attribute accuracy.

Contribution

The proposed framework is lightweight, adaptive, and attribute-aware, improving multi-aspect controllable text generation by dynamically adjusting parameters and handling data discrepancies.

Findings

Outperforms strong baselines in experiments.

Achieves state-of-the-art performance.

Demonstrates good adaptation to data discrepancies.

Abstract

Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this task due to their simplicity and effectiveness. However, they still have some limitations: low rank adaptation (LoRA) only fine-tunes a few parameters and has suboptimal control effects, while full fine-tuning (FFT) requires significant computational resources and is susceptible to overfitting, particularly when data is limited. Moreover, existing works typically train multi-aspect controllable text generation models using only single-aspect annotated data, which results in discrepancies in data distribution; at the same time, accurately generating text with specific attributes is a challenge that requires strong attribute-aware capabilities. To address these limitations, we propose a lightweight, adaptive and attribute-aware framework for multi-aspect controllable text generation. Our framework can dynamically adjust model parameters according to different aspects of data to achieve controllable text generation, aiming to optimize performance across multiple aspects. Experimental results show that our framework outperforms other strong baselines, achieves state-of-the-art performance, adapts well to data discrepancies, and is more accurate in attribute perception.