用于缓解大型语言模型知识蒸馏中幻觉问题的交互式 DualChecker
Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models
AI总结：
提出 DualChecker 框架，通过 ContextAligner 对齐标注标准与动态检查器增强模型交互，有效缓解知识蒸馏中的幻觉问题，使教师和学生模型 F1 分数分别提升 17% 和 10%。
摘要：
大型语言模型（LLMs）在各种机器学习（ML）任务中展现出了卓越的能力。鉴于为监督学习创建标注数据集的成本高昂，LLMs 通过实现有效的少样本上下文学习提供了一种有价值的替代方案。然而，这些模型会产生幻觉，特别是在知识不完整的领域中。此外，当前使用 LLMs 进行知识蒸馏的方法往往难以同时提升教师模型和学生模型的有效性。为了应对这些挑战，我们引入了 DualChecker，这是一个旨在缓解幻觉并提升知识蒸馏过程中教师模型和学生模型性能的创新框架。DualChecker 采用 ContextAligner 来确保教师模型提供的上下文符合人类标注标准。它还配备了一个增强模型交互的动态检查器系统：当教师模型表现出低置信度时，一个组件会用更详细的内容重新提示教师模型；另一个组件则从学生模型中识别边界情况以优化教学模板。这种交互过程促进了模型间的持续改进和有效的知识转移。我们使用包含二分类、多分类和 token 分类任务的绿色创新文本数据集对 DualChecker 进行了评估。实验结果表明，DualChecker 显著优于现有的最先进方法，教师模型的 F1 分数提升了高达 17%，学生模型提升了 10%。值得注意的是，使用 LLM 预测微调的学生模型表现与使用真实数据微调的模型相当，即使在具有挑战性的领域也是如此。我们将本研究中的所有数据集、模型和代码公开发布。
英文摘要：
Large Language Models (LLMs) have demonstrated exceptional capabilities across various machine learning (ML) tasks. Given the high costs of creating annotated datasets for supervised learning, LLMs offer a valuable alternative by enabling effective few-shot in-context learning. However, these models can produce hallucinations, particularly in domains with incomplete knowledge. Additionally, current methods for knowledge distillation using LLMs often struggle to enhance the effectiveness of both teacher and student models. To address these challenges, we introduce DualChecker, an innovative framework designed to mitigate hallucinations and improve the performance of both teacher and student models during knowledge distillation. DualChecker employs ContextAligner to ensure that the context provided by teacher models aligns with human labeling standards. It also features a dynamic checker system that enhances model interaction: one component re-prompts teacher models with more detailed content when they show low confidence, and another identifies borderline cases from student models to refine the teaching templates. This interactive process promotes continuous improvement and effective knowledge transfer between the models. We evaluate DualChecker using a green innovation textual dataset that includes binary, multiclass, and token classification tasks. The experimental results show that DualChecker significantly outperforms existing state-of-the-art methods, achieving up to a 17% improvement in F1 score for teacher models and 10% for student models. Notably, student models fine-tuned with LLM predictions perform comparably to those fine-tuned with actual data, even in a challenging domain. We make all datasets, models, and code from this research publicly available.
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。
