Multi-Novelty：通过推理时多视角头脑风暴提升大语言模型生成内容的多样性与新颖性
Multi-Novelty: Improve the Diversity and Novelty of Contents Generated by Large Language Models via inference-time Multi-Views Brainstorming
AI总结：
针对大语言模型生成内容重复、缺乏新颖性的问题，本文提出推理时多视角头脑风暴方法 Multi-Novelty，利用文本与视觉来源丰富提示并作为思维链起点，且无需修改模型架构。
摘要：
大语言模型（LLM）在生成准确且流畅的文本方面表现出显著能力。然而，它们在多样性和新颖性方面常遇困难，导致回复重复或过于确定性。这些局限源于训练数据中的约束，包括特定知识领域的空白、信息过时以及对文本来源的过度依赖。此类缺陷降低了它们在需要创造力、多视角推理和探索性思维的任务中的有效性，例如基于 LLM 的 AI 科学家智能体和创意艺术家智能体。为应对这一挑战，我们提出推理时多视角头脑风暴方法，这是一种利用来自文本和视觉来源的多样视角丰富输入提示的新颖方法，我们将其称为“Multi-Novelty”。通过纳入额外的上下文信息作为思维链的多样起点，该方法增强了生成输出的多样性和创造性。重要的是，我们的方法与模型无关，无需架构修改，并且兼容开源和专有 LLM。
英文摘要：
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 These limitations stem from constraints in training data, including gaps in specific knowledge domains, outdated information, and an over-reliance on textual sources.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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
