Large language models (LLMs) often struggle with temporal reasoning, crucial
for tasks like historical event analysis and time-sensitive information
retrieval. Despite advancements, state-of-the-art models falter in handling
temporal information, especially when faced with irrelevant or noisy contexts.
This paper addresses this gap by empirically examining the robustness of
temporal question-answering (TQA) systems trained on various context types,
including relevant, irrelevant, slightly altered, and no context. Our findings
indicate that training with a mix of these contexts enhances model robustness
and accuracy. Additionally, we show that the position of context relative to
the question significantly impacts performance, with question-first positioning
yielding better results. We introduce two new context-rich TQA datasets,
ContextAQA and ContextTQE, and provide comprehensive evaluations and guidelines
for training robust TQA models. Our work lays the foundation for developing
reliable and context-aware temporal QA systems, with broader implications for
enhancing LLM robustness against diverse and potentially adversarial
information.

该论文通过经验性地考察训练在各种上下文类型中的时间问答（TQA）系统的鲁棒性，填补大型语言模型（LLM）在处理时态信息方面的不足，发现在涵盖相关、无关、稍微改动和无上下文的混合情况下训练，能增强模型的鲁棒性和准确性，并且问题先于上下文的位置布局有着明显影响。提出了两个新的上下文丰富的 TQA 数据集，ContextAQA 和 ContextTQE，并提供了全面的评估和指南，为培养鲁棒的 TQA 模型奠定了基础，对加强 LLM 在面对多样化和潜在对抗性信息时的鲁棒性具有广泛的影响。

上下文的重要性：对时间问答系统中上下文信息影响的实证研究

Context Matters: An Empirical Study of the Impact of Contextual  Information in Temporal Question Answering Systems

We provide the first extensive evaluation of how using different types of
context to learn skip-gram word embeddings affects performance on a wide range
of intrinsic and extrinsic NLP tasks. Our results suggest that while intrinsic
tasks tend to exhibit a clear preference to particular types of contexts and
higher dimensionality, more careful tuning is required for finding the optimal
settings for most of the extrinsic tasks that we considered. Furthermore, for
these extrinsic tasks, we find that once the benefit from increasing the
embedding dimensionality is mostly exhausted, simple concatenation of word
embeddings, learned with different context types, can yield further performance
gains. As an additional contribution, we propose a new variant of the skip-gram
model that learns word embeddings from weighted contexts of substitute words.

本文通过对不同类型的上下文学习 skip-gram 词嵌入对广泛的内在和外在自然语言处理任务性能的首次全面评估，发现内在任务在特定类型的上下文和更高的维度方面更好，而对于大多数外在任务，需要更仔细的调整来找到最佳设置；另外，对于这些外在任务，一旦提高嵌入维度的好处大多用尽，使用不同上下文类型学习的简单词嵌入的串联，可以产生进一步的性能提升；此外，本文还提出了一种新的 skip-gram 模型变体，从替换词的加权上下文中学习单词嵌入。