arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2210.01258cs.CLcs.AI
收藏

基于转换器的语言表征模型中先验偏差和选择麻痹的四个实验探索

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

Information Sciences Institute, University of Southern California(南加州大学信息科学研究所)

Ke Shen, Mayank Kejriwal

摘要:

最近在基于transformer的神经网络上的工作已经在多选择自然语言理解(NLU)问题上取得了令人印象深刻的进展,例如问答(QA)和溯因推理。尽管取得了这些进展,但在理解这些模型是否以足够稳健的方式对受干扰的多项选择实例做出响应,从而使它们在现实世界中值得信赖方面,工作仍然有限。我们提出了四个混淆探针,灵感来自于行为科学界首次发现的类似现象,以测试先验偏见和选择麻痹等问题。在实验中,我们使用四个已建立的基准数据集探测了一个广泛使用的基于transformer的多选NLU系统。在这里,我们表明,该模型表现出显着的先验偏差和较小的,但仍然非常显着的程度,选择瘫痪,除了其他问题。我们的研究结果表明,更强的测试协议和额外的基准可能是必要的,在语言模型用于面向前端的系统或决策与现实世界的后果。

英文摘要:

Recent work on transformer-based neural networks has led to impressive advances on multiple-choice natural language understanding (NLU) problems, such as Question Answering (QA) and abductive reasoning. Despite these advances, there is limited work still on understanding whether these models respond to perturbed multiple-choice instances in a sufficiently robust manner that would allow them to be trusted in real-world situations. We present four confusion probes, inspired by similar phenomena first identified in the behavioral science community, to test for problems such as prior bias and choice paralysis. Experimentally, we probe a widely used transformer-based multiple-choice NLU system using four established benchmark datasets. Here we show that the model exhibits significant prior bias and to a lesser, but still highly significant degree, choice paralysis, in addition to other problems. Our results suggest that stronger testing protocols and additional benchmarks may be necessary before the language models are used in front-facing systems or decision making with real world consequences.

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。

↑