arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.07151cs.CL
收藏

人类与机器的过度信息问答

Overinformative Question Answering by Humans and Machines

University of Tübingen(图宾根大学);Princeton University(普林斯顿大学);Stanford University(斯坦福大学)

Polina Tsvilodub, Michael Franke, Robert D. Hawkins, Noah D. Goodman

AI总结:

本文通过实验证明人类回答极性问句时的过度信息性受相关性驱动,并评估神经语言模型,发现多数模型表现不佳,GPT-3仅在特定提示下接近人类表现。

摘要:

面对极性问句时,说话者常常提供超出简单“是”或“否”的过度信息回答。但指导额外信息选择的原理是什么?在本文中,我们通过两项研究提供了实验证据,表明人类回答中的过度信息性是由对提问者目标的相关性考虑所驱动的,并且他们会根据提问所处的功能语境灵活调整这种考虑。我们将这些人类结果作为强基准,用于研究最先进的神经语言模型在问答任务中的表现,并对人类实验中的项目进行了广泛评估。我们发现,大多数模型未能以类似人类的方式调整其回答行为,并且倾向于包含无关信息。我们表明,GPT-3对提示形式高度敏感,只有在有示例和认知动机解释的引导下,才能达到类似人类的回答模式。

英文摘要:

When faced with a polar question, speakers often provide overinformative answers going beyond a simple "yes" or "no". But what principles guide the selection of additional information? In this paper, we provide experimental evidence from two studies suggesting that overinformativeness in human answering is driven by considerations of relevance to the questioner's goals which they flexibly adjust given the functional context in which the question is uttered. We take these human results as a strong benchmark for investigating question-answering performance in state-of-the-art neural language models, conducting an extensive evaluation on items from human experiments. We find that most models fail to adjust their answering behavior in a human-like way and tend to include irrelevant information. We show that GPT-3 is highly sensitive to the form of the prompt and only achieves human-like answer patterns when guided by an example and cognitively-motivated explanation.

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。

↑