让AI理解人类心理预期，自动生成更符合评审口味的体育报道。
Automated Meta Prompt Engineering for Alignment with the Theory of Mind
- 用AI当裁判，通过试错优化生成内容以匹配人类心理期待。
- 在美网赛事中，人类评审与AI生成内容完全对齐率达53.8%。
- 适合需要高契合度内容生成的体育娱乐实时报道场景。
我们提出一种元提示方法，联合生成流畅文本并优化人类心理预期与大语言模型神经状态间的相似性。采用代理强化学习机制，由一个作为裁判的LLM（LLMaaJ）通过上下文学习指导另一模型生成内容，识别有意与无意的文本特征。为衡量人类对内容创作的心理预期，用户在2024年美国网球公开赛前修改长篇生成文章。结果表明，LLMaaJ能通过预判人类修改实现理论心智（ToM）对齐，在实际系统测试中，人类评审期望与AI输出一致率达53.8%，平均迭代4.38次达到100%对齐。通过希尔伯特空间中的几何表示，将事实性、新颖性、重复性、相关性等特质的空间体积与顶点对齐相结合，使LLMaaJ有效优化人类心智。该方法显著提升内容质量，扩展了网球动作描述覆盖范围。本工作已部署于美网2024，并推广至其他体育与娱乐实时事件。
原文摘要 · Abstract (English)
We introduce a method of meta-prompting that jointly produces fluent text for complex tasks while optimizing the similarity of neural states between a human's mental expectation and a Large Language Model's (LLM) neural processing. A technique of agentic reinforcement learning is applied, in which an LLM as a Judge (LLMaaJ) teaches another LLM, through in-context learning, how to produce content by interpreting the intended and unintended generated text traits. To measure human mental beliefs around content production, users modify long form AI-generated text articles before publication at the US Open 2024 tennis Grand Slam. Now, an LLMaaJ can solve the Theory of Mind (ToM) alignment problem by anticipating and including human edits within the creation of text from an LLM. Throughout experimentation and by interpreting the results of a live production system, the expectations of human content reviewers had 100% of alignment with AI 53.8% of the time with an average iteration count of 4.38. The geometric interpretation of content traits such as factualness, novelty, repetitiveness, and relevancy over a Hilbert vector space combines spatial volume (all trait importance) with vertices alignment (individual trait relevance) enabled the LLMaaJ to optimize on Human ToM. This resulted in an increase in content quality by extending the coverage of tennis action. Our work that was deployed at the US Open 2024 has been used across other live events within sports and entertainment.
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。