通过迭代注入与优化概念，提升大模型的创造性输出。
Initial Development and Evaluation of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) System
- 采用概念反复注入与迭代优化，增强大模型创造力。
- 实验验证了系统核心组件在提升创意质量上的有效性。
- 适合对生成式AI创造力提升感兴趣的开发者与研究者。
计算机系统创造力是迈向通用人工智能（AGI）的关键步骤，但因人类创造力尚未被完全理解，难以在软件中实现。大语言模型（LLMs）虽能模拟创意与意识表象，却并非真正具备创造力或意识。尽管LLMs已生成真实新内容，但在某些情况下（如有害幻觉）是无意的，其有意创造能力仍被认为不及人类。为应对这一挑战，本文提出一种通过概念反复注入与迭代优化来增强LLM输出创造力的技术。初步介绍了创意人工智能通过反复发展与决策（CAIRDD）系统的开发，并评估了其关键组件的有效性。
原文摘要 · Abstract (English)
Computer system creativity is a key step on the pathway to artificial general intelligence (AGI). It is elusive, however, due to the fact that human creativity is not fully understood and, thus, it is difficult to develop this capability in software. Large language models (LLMs) provide a facsimile of creativity and the appearance of sentience, while not actually being either creative or sentient. While LLMs have created bona fide new content, in some cases - such as with harmful hallucinations - inadvertently, their deliberate creativity is seen by some to not match that of humans. In response to this challenge, this paper proposes a technique for enhancing LLM output creativity via an iterative process of concept injection and refinement. Initial work on the development of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) system is presented and the efficacy of key system components is evaluated.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。