大型语言模型中用户控制的知识融合：平衡创造性与幻觉
User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination
AI总结：
本文提出一种用户可控机制，通过在LLMs微调阶段引入基于ROUGE、Sentence-BERT和自评估计算的忠实度数值标签，使用户能在推理时控制模型对外部知识的依赖，从而平衡创造性与幻觉。
摘要：
在现代对话系统中，由于大型语言模型（LLMs）能够生成多样化、相关且具有创造性的回复，其使用量呈指数级增长。尽管具有这些优势，如何在LLMs的创造性与对外部知识的忠实度之间取得平衡仍然是一个关键挑战。本文提出了一种创新的用户可控机制，该机制可以调节LLMs的想象力与其对事实信息遵循之间的平衡。我们的方法在LLMs训练的微调阶段引入了一个数值标签，表示在生成的回复中对参考知识的忠实度。该忠实度通过一个自动化过程计算，该过程使用ROUGE分数测量词汇重叠，使用Sentence-BERT嵌入测量语义相似度，并使用LLMs的自我评估分数。在模型推理期间，用户可以操纵这个数值标签，从而控制LLMs对外部知识的依赖程度。我们在各种场景下进行了大量实验，证明了我们方法的适应性及其在确保LLMs回复质量和准确性方面的有效性。结果突显了我们的方法在增强LLMs多功能性的同时，保持创造性与幻觉之间平衡的潜力。
英文摘要：
In modern dialogue systems, the use of Large Language Models (LLMs) has grown exponentially due to their capacity to generate diverse, relevant, and creative responses. Despite their strengths, striking a balance between the LLMs' creativity and their faithfulness to external knowledge remains a key challenge. This paper presents an innovative user-controllable mechanism that modulates the balance between an LLM's imaginative capabilities and its adherence to factual information. Our approach incorporates a numerical tag during the fine-tuning phase of the LLM's training, representing the degree of faithfulness to the reference knowledge in the generated responses. This degree is computed through an automated process that measures lexical overlap using ROUGE scores, semantic similarity using Sentence-BERT embeddings, and an LLM's self-evaluation score. During model inference, users can manipulate this numerical tag, thus controlling the degree of the LLM's reliance on external knowledge. We conduct extensive experiments across various scenarios, demonstrating the adaptability of our method and its efficacy in ensuring the quality and accuracy of the LLM's responses. The results highlight the potential of our approach to enhance the versatility of LLMs while maintaining a balance between creativity and hallucination.
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。
