一种用于幻觉缓解的进化大语言模型
An Evolutionary Large Language Model for Hallucination Mitigation
AI总结：
本文提出受进化计算启发的EvoLLMs框架，利用遗传算法自动生成高质量问答数据集以缓解大语言模型幻觉，实验表明其在深度、相关性和覆盖率上优于人工数据集，并接近人类幻觉缓解水平。
摘要：
以ChatGPT和Gemini为代表的大语言模型（LLMs）的出现，标志着人工智能应用进入现代阶段，其特点是能够生成文本、图像和视频的高影响力应用。然而，这些模型通常伴随一个关键挑战，即幻觉：自信地呈现不准确或捏造的信息。当这些模型应用于医疗和法律等专业领域时，这一问题引发严重关切，因为在这些领域中信息的准确性和精确性是绝对条件。在本文中，我们提出了EvoLLMs，这是一个受进化计算启发的创新框架，能够在最小化幻觉的同时自动生成高质量的问答（QA）数据集。EvoLLMs采用遗传算法，模拟选择、变异和突变等进化过程，引导大语言模型生成准确且上下文相关的问答对。对比分析表明，EvoLLMs在深度、相关性和覆盖率等关键指标上持续优于人工生成的数据集，同时在缓解幻觉方面几乎达到人类表现水平。这些结果凸显了EvoLLMs作为问答数据集生成的稳健且高效解决方案的价值，显著减少了人工整理所需的时间和资源。
英文摘要：
The emergence of LLMs, like ChatGPT and Gemini, has marked the modern era of artificial intelligence applications characterized by high-impact applications generating text, images, and videos. However, these models usually ensue with one critical challenge called hallucination: confident presentation of inaccurate or fabricated information. This problem attracts serious concern when these models are applied to specialized domains, including healthcare and law, where the accuracy and preciseness of information are absolute conditions. In this paper, we propose EvoLLMs, an innovative framework inspired by Evolutionary Computation, which automates the generation of high-quality Question-answering (QA) datasets while minimizing hallucinations. EvoLLMs employs genetic algorithms, mimicking evolutionary processes like selection, variation, and mutation, to guide LLMs in generating accurate, contextually relevant question-answer pairs. Comparative analysis shows that EvoLLMs consistently outperforms human-generated datasets in key metrics such as Depth, Relevance, and Coverage, while nearly matching human performance in mitigating hallucinations. These results highlight EvoLLMs as a robust and efficient solution for QA dataset generation, significantly reducing the time and resources required for manual curation.
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。
