DYNAMICQA：追踪语言模型中的内部知识冲突
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
AI总结：
该研究构建了包含真实世界动态冲突知识的DynamicQA数据集，提出连贯说服分数等冲突度量方法，证实语言模型对动态事实的内存内冲突程度更高，且这类事实更难通过上下文更新，为检索增强生成的优化提供了参考。
摘要：
知识密集型语言理解任务要求语言模型（LMs）整合相关上下文，以缓解其固有的缺陷，例如知识不完整或过时。然而，语言模型的参数中可能存在冲突知识，称为内存内冲突，这会影响模型接受上下文知识的倾向。为研究内存内冲突对语言模型接受相关上下文能力的影响，我们采用两种知识冲突度量方法，并构建了一个包含固有冲突数据的新型数据集DynamicQA。该数据集包含具有时间动态性的事实（这类事实会随时间变化）以及有争议的动态事实（这类事实会因观点不同而改变）。DynamicQA是首个纳入真实世界知识冲突并提供相关上下文以研究不同类型知识冲突之间关联的数据集。我们还评估了语义熵和一种新型的连贯说服分数这两种度量方法反映内存内冲突存在的能力。通过大量实验，我们证实：与具有单一真值的事实相比，语言模型在动态事实中表现出更高程度的内存内冲突。此外，我们发现存在内存内冲突的事实更难通过上下文更新，这表明检索增强生成在处理最常被调整的事实时会遇到困难。
英文摘要：
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. However, conflicting knowledge can be present in the LM's parameters, termed intra-memory conflict, which can affect a model's propensity to accept contextual knowledge. To study the effect of intra-memory conflict on an LM's ability to accept relevant context, we utilize two knowledge conflict measures and a novel dataset containing inherently conflicting data, DynamicQA. This dataset includes facts with a temporal dynamic nature where facts can change over time and disputable dynamic facts, which can change depending on the viewpoint. DynamicQA is the first to include real-world knowledge conflicts and provide context to study the link between the different types of knowledge conflicts. We also evaluate several measures on their ability to reflect the presence of intra-memory conflict: semantic entropy and a novel coherent persuasion score. With our extensive experiments, we verify that LMs exhibit a greater degree of intra-memory conflict with dynamic facts compared to facts that have a single truth value. Furthermore, we reveal that facts with intra-memory conflict are harder to update with context, suggesting that retrieval-augmented generation will struggle with the most commonly adapted facts.
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。
