区分异常句与真正无意义句，发现多数句子仅需上下文即可理解。
Finding Sense in Nonsense with Generated Contexts: Perspectives from Humans and Language Models
- 通过人类与大模型标注，评估五大数据集中句子的语义合理性。
- 多数句子被判定为可解释的异常句，仅少数真正无意义。
- 大模型能有效生成合理上下文，帮助理解异常句。
无意义和异常句子在语义理解模型发展中起到关键作用。核心挑战在于区分仅异常（但可通过上下文解释）与真正无意义的句子。然而，现有数据集究竟有多无意义尚不明确，且大语言模型在此类判断上的表现也未知。本文通过收集人类评判者和大模型对五个语义偏离数据集中的句子（无上下文与有上下文两种情况）的语义合理性判断，发现大多数句子仅被视为异常而非真正无意义；同时，大模型在为异常句生成合理上下文方面表现出显著能力。
原文摘要 · Abstract (English)
Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge is to distinguish between what is merely anomalous (but can be interpreted given a supporting context) and what is truly nonsensical. However, it is unclear (a) how nonsensical, rather than merely anomalous, existing datasets are; and (b) how well LLMs can make this distinction. In this paper, we answer both questions by collecting sensicality judgments from human raters and LLMs on sentences from five semantically deviant datasets: both context-free and when providing a context. We find that raters consider most sentences at most anomalous, and only a few as properly nonsensical. We also show that LLMs are substantially skilled in generating plausible contexts for anomalous cases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。