AdaCAD：自适应解码以平衡上下文知识与参数化知识之间的冲突
AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
AI总结：
提出AdaCAD自适应解码方法，通过Jensen-Shannon散度动态推断调整权重以平衡LLM上下文与参数知识冲突，显著提升QA准确率和摘要事实性。
摘要：
知识冲突源于大型语言模型（LLM）上下文中的信息与其参数中存储的知识之间的差异。当使用标准的解码技术时，这可能会损害性能，因为标准解码倾向于忽略上下文。现有的测试时对比方法试图通过比较LLM在有上下文和没有上下文情况下的输出分布来解决这个问题，并根据它们之间的对比来调整模型。然而，我们发现这些方法经常误判冲突的程度，并且难以处理冲突量不同的实例，静态方法在不存在冲突时会过度调整。我们提出了一种名为AdaCAD的细粒度实例级方法，该方法根据冲突程度动态推断调整权重，冲突程度由代表上下文知识和参数化知识的分布之间的Jensen-Shannon散度来衡量。在四个LLM、六个问答（QA）和三个摘要数据集上，我们证明ADACAD始终优于其他解码基线，与静态对比基线相比，QA平均准确率绝对提高了14.21%，并且摘要的事实性提高了6.19（AlignScore）。最后，我们表明，虽然对比基线在不存在冲突时会损害性能，但ADACAD减轻了这些损失，使其更适用于一些示例存在冲突而另一些不存在冲突的真实世界数据集。
英文摘要：
Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. This can hurt performance when using standard decoding techniques, which tend to ignore the context. Existing test-time contrastive methods seek to address this by comparing the LLM's output distribution with and without the context and adjust the model according to the contrast between them. However, we find that these methods frequently misjudge the degree of conflict and struggle to handle instances that vary in their amount of conflict, with static methods over-adjusting when conflict is absent. We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict, as measured by the Jensen-Shannon divergence between distributions representing contextual and parametric knowledge. Across four LLMs, six question-answering (QA) and three summarization datasets, we demonstrate that ADACAD consistently outperforms other decoding baselines with average QA accuracy gains of 14.21% (absolute) over a static contrastive baseline, and improves the factuality of summaries by 6.19 (AlignScore). Lastly, we show that while contrastive baselines hurt performance when conflict is absent, ADACAD mitigates these losses, making it more applicable to real-world datasets in which some examples have conflict and others do not.
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。
