通过基于扰动的系统响应合成数据生成增强幻觉检测
Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses
AI总结：
针对幻觉检测标注昂贵且易过时的问题，提出通过改写系统响应自动构造忠实与幻觉样本的数据生成方法，使微调后的T5-base在准确率和延迟上优于现有零样本检测器与合成方法。
摘要：
检测大型语言模型（LLM）输出中的幻觉至关重要，但为该分类任务进行传统微调受到标注过程昂贵且很快过时的阻碍，尤其是在众多垂直领域以及面对LLM快速发展时。本研究提出一种通过改写系统响应自动生成忠实输出和幻觉输出的方法。实验结果表明，在我们生成的数据集上微调的T5-base模型，在准确率和延迟方面均优于最先进的零样本检测器及现有合成生成方法，表明该方法有效。
英文摘要：
Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical domains and in the face of rapid LLM advancements. In this study, we introduce an approach that automatically generates both faithful and hallucinated outputs by rewriting system responses. Experimental findings demonstrate that a T5-base model, fine-tuned on our generated dataset, surpasses state-of-the-art zero-shot detectors and existing synthetic generation methods in both accuracy and latency, indicating efficacy of our approach.
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。
