语言模型的幻觉增强复述
Hallucination Augmented Recitations for Language Models
AI总结：
提出幻觉增强复述（HAR）方法，利用LLM幻觉生成反事实数据集以增强开放书问答的归因能力，实验显示F1最高提升8.0%，且在小模型和小数据集上仍优于人类标注数据。
摘要：
归因是大语言模型（LLMs）中的一个关键概念，因为它能够控制信息来源并增强LLMs的事实性。虽然现有方法利用开放书问答来提高归因能力，但事实数据集可能会奖励语言模型回忆它们从预训练数据中已知的事实，而非归因。相比之下，反事实开放书问答数据集将进一步改善归因，因为答案只能基于给定文本。我们提出了幻觉增强复述（HAR），通过利用LLMs中的幻觉来创建反事实数据集，以提高归因能力。以开放书问答为案例研究，我们证明了使用我们的反事实数据集微调的模型改善了文本基础，从而提高了开放书问答性能，F1分数最高提升8.0%。我们的反事实数据集在使用比人类标注的事实数据集小4倍的数据集和4倍小的模型时，仍能显著优于后者。我们观察到，这种改进在各种模型大小和数据集上都是一致的，包括多跳、生物医学和对抗性问答数据集。
英文摘要：
Attribution is a key concept in large language models (LLMs) as it enables control over information sources and enhances the factuality of LLMs. While existing approaches utilize open book question answering to improve attribution, factual datasets may reward language models to recall facts that they already know from their pretraining data, not attribution. In contrast, counterfactual open book QA datasets would further improve attribution because the answer could only be grounded in the given text. We propose Hallucination Augmented Recitations (HAR) for creating counterfactual datasets by utilizing hallucination in LLMs to improve attribution. For open book QA as a case study, we demonstrate that models finetuned with our counterfactual datasets improve text grounding, leading to better open book QA performance, with up to an 8.0% increase in F1 score. Our counterfactual dataset leads to significantly better performance than using humanannotated factual datasets, even with 4x smaller datasets and 4x smaller models. We observe that improvements are consistent across various model sizes and datasets, including multi-hop, biomedical, and adversarial QA datasets.
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。
