跳出（灰色）框：一种基于上下文的评分，用于评估神经文本生成的价值与原创性
Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation
AI总结：
该研究针对大型语言模型生成文本缺乏多样性的问题，提出基于信息论的上下文评分，将其作为强化学习的奖励微调模型，在诗歌、数学题等任务中提升生成内容的价值与原创性。
摘要：
尽管大型语言模型在创意任务中的应用日益广泛，但其输出往往缺乏多样性。常见的解决方案，如在更高温度下采样，可能会损害结果的质量。处理这种权衡仍是设计创意类人工智能系统时的开放性挑战。基于信息论，我们提出一种基于上下文的评分，用于定量评估价值与原创性。该评分在激励准确性和对请求的依从性的同时，促进与学习到的分布的偏差。我们表明，该评分可作为强化学习框架中的奖励，用于微调大型语言模型以实现最佳性能。我们通过涵盖诗歌生成、数学问题求解等多种创意任务的实验验证了该策略，证明其能提升生成解决方案的价值与原创性。
英文摘要：
Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling at higher temperatures, can compromise the quality of the results. Dealing with this trade-off is still an open challenge in designing AI systems for creativity. Drawing on information theory, we propose a context-based score to quantitatively evaluate value and originality. This score incentivizes accuracy and adherence to the request while fostering divergence from the learned distribution. We show that our score can be used as a reward in a reinforcement learning framework to fine-tune large language models for maximum performance. We validate our strategy through experiments considering a variety of creative tasks, such as poetry generation and math problem solving, demonstrating that it enhances the value and originality of the generated solutions.
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。
