MOPO: Multi-Objective Prompt Optimization for Affective Text Generation

TL;DR

MOPO is a multi-objective prompt optimization method that generates diverse prompts for affective text generation, enabling better domain-specific emotion expression with improved performance and efficiency.

Contribution

We introduce MOPO, a novel multi-objective prompt optimization approach that produces a set of prompts balancing multiple emotion-related objectives for domain-specific text generation.

Findings

MOPO improves performance by up to 15 percentage points across objectives.

MOPO maintains minimal performance loss (1-2 percentage points) for individual objectives.

MOPO reduces computational requirements by optimizing multiple objectives simultaneously.

Abstract

How emotions are expressed depends on the context and domain. On X (formerly Twitter), for instance, an author might simply use the hashtag #anger, while in a news headline, emotions are typically written in a more polite, indirect manner. To enable conditional text generation models to create emotionally connotated texts that fit a domain, users need to have access to a parameter that allows them to choose the appropriate way to express an emotion. To achieve this, we introduce MOPO, a Multi-Objective Prompt Optimization methodology. MOPO optimizes prompts according to multiple objectives (which correspond here to the output probabilities assigned by emotion classifiers trained for different domains). In contrast to single objective optimization, MOPO outputs a set of prompts, each with a different weighting of the multiple objectives. Users can then choose the most appropriate prompt for their context. We evaluate MOPO using three objectives, determined by various domain-specific emotion classifiers. MOPO improves performance by up to 15 pp across all objectives with a minimal loss (1-2 pp) for any single objective compared to single-objective optimization. These minor performance losses are offset by a broader generalization across multiple objectives - which is not possible with single-objective optimization. Additionally, MOPO reduces computational requirements by simultaneously optimizing for multiple objectives, eliminating separate optimization procedures for each objective.