Abstract
Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks (e.g., knowledge acquisition tasks). In this paper, we seek to assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention. We demonstrate that LLMs' faithfulness can be significantly improved using carefully designed prompting strategies. In particular, we identify opinion-based prompts and counterfactual demonstrations as the most effective methods. Opinion-based prompts reframe the context as a narrator's statement and inquire about the narrator's opinions, while counterfactual demonstrations use instances containing false facts to improve faithfulness in knowledge conflict situations. Neither technique requires additional training. We conduct experiments on three datasets of two standard NLP tasks, machine reading comprehension and relation extraction, and the results demonstrate significant improvement in faithfulness to contexts.
Abstract (translated)
大型语言模型(LLMs)编码了对世界事实的参数知识,并在知识驱动的NLP任务中表现出出色的性能。然而,他们依赖参数知识可能会导致他们忽略上下文线索,从而导致在上下文敏感的NLP任务(例如知识获取任务)中错误的预测。在本文中,我们希望评估和增强LLMs的上下文准确性,两个方面:知识冲突和预测并保持中立。我们证明了使用精心设计的prompting策略,可以显著改善LLMs的上下文准确性。特别是,我们确定了基于意见的prompt和反事实演示是最有效的方法。基于意见的prompt将上下文改写为主持人的声明,并询问主持人的意见,而反事实演示则使用包含虚假事实的例子来改善知识冲突情况下的上下文准确性。两种方法都不需要额外的训练。我们对两个标准NLP任务的三个数据集进行了实验,即机器阅读理解和关系提取,结果表明,在上下文准确性方面取得了显著的改善。
URL
https://arxiv.org/abs/2303.11315
