Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization

TL;DR

This paper introduces MAGIC-HMO, a novel framework for Chinese short-form creative language generation that jointly optimizes multiple constraints and explanation reliability using a multi-agent, multi-objective approach.

Contribution

It formalizes Chinese short-form content generation as a heterogeneous multi-objective optimization problem and proposes a training-free framework that outperforms existing methods.

Findings

MAGIC-HMO significantly outperforms six strong baselines.

The framework effectively balances multiple personalized constraints.

Experiments on Chinese Baby Naming demonstrate its robustness.

Abstract

Chinese demonstrates high semantic compactness and rich metaphorical expressiveness, enabling limited text to convey dense meanings while increasing the difficulty of generation and verification, particularly in short-form creative natural language generation (CNLG). In the real world, users often require personalized, fine-grained creative constraints, making reliable verification critical to guiding optimization. According to Brunswik's Lens Model from psychology, constraints' achievement can be inferred from sufficient observable cues. Existing studies are mainly outcome-oriented, implicitly assuming that the outcome itself provides adequate cues for verification. However, this assumption breaks down in Chinese short-form CNLG (e.g., naming or advertising) with diverse personalized constraints, where extremely brief outcomes inherently offer limited information. Explanations can naturally serve as extra cues. Nevertheless, under complex constraints, LLMs' explanations may suffer from hallucination, incompleteness, or ambiguity. To address these, we novelly formalize the Chinese short-form CNLG task as a heterogeneous multi-objective optimization (HMO) issue that needs to jointly optimize multiple personalized constraints and explanation reliability. We further propose MAGIC-HMO, a training-free multi-agent framework that optimizes these objectives through iterative generation and verification under an explanation-oriented multi-objective strategy. Experiments on \emph{Chinese Baby Naming}, a challenging benchmark, demonstrate that MAGIC-HMO significantly outperforms six strong baselines across various LLM backbones. Relevant data and codes are available at https://github.com/foolfun/MAGIC_HMO.