Multi-Novelty: Improve the Diversity and Novelty of Contents Generated by Large Language Models via inference-time Multi-Views Brainstorming

TL;DR

This paper introduces a model-agnostic inference-time multi-view brainstorming method that enhances the diversity and novelty of outputs generated by large language models by incorporating diverse textual and visual perspectives.

Contribution

The paper proposes a novel inference-time multi-view brainstorming approach that enriches prompts with diverse perspectives to improve content diversity and creativity in LLM outputs.

Findings

Enhanced diversity and novelty in generated content.

Compatible with various LLM architectures without modifications.

Improved performance in creative and exploratory tasks.

Abstract

Large Language Models (LLMs) demonstrate remarkable proficiency in generating accurate and fluent text. However, they often struggle with diversity and novelty, leading to repetitive or overly deterministic responses. These limitations stem from constraints in training data, including gaps in specific knowledge domains, outdated information, and an over-reliance on textual sources. Such shortcomings reduce their effectiveness in tasks requiring creativity, multi-perspective reasoning, and exploratory thinking, such as LLM based AI scientist agents and creative artist agents . To address this challenge, we introduce inference-time multi-view brainstorming method, a novel approach that enriches input prompts with diverse perspectives derived from both textual and visual sources, which we refere to as "Multi-Novelty". By incorporating additional contextual information as diverse starting point for chain of thoughts, this method enhances the variety and creativity of generated outputs. Importantly, our approach is model-agnostic, requiring no architectural modifications and being compatible with both open-source and proprietary LLMs.