arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.05338cs.CL
收藏

利用归因分数解释预训练语言模型:低资源场景下的分析

Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings

Bosch Center for Artificial Intelligence(博世人工智能中心);University of Stuttgart(斯图加特大学);Hochschule der Medien(媒体大学);Technical University of Darmstadt(达姆施塔特工业大学)

Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu

AI总结:

本研究针对低资源场景下基于提示的模型归因分数质量未被探究的问题,纳入训练规模维度对比提示范式、微调模型及大语言模型的归因质量,发现低资源下提示范式解释更合理,沙普利值采样表现优于注意力和积分梯度。

摘要:

归因分数可指示不同输入部分的重要性,因此能够解释模型行为。当前,基于提示的模型正日益流行,部分原因是其在低资源场景下更易适配。然而,从基于提示的模型中提取的归因分数的质量尚未得到研究。在本研究中,我们围绕这一主题,分析从基于提示的模型中提取的归因分数的合理性与忠实性,并将其与从微调模型及大语言模型中提取的归因分数进行对比。与以往研究不同,我们将训练规模作为另一个维度纳入分析。我们发现,在低资源场景下,使用提示范式(无论是基于编码器还是基于解码器的模型)都能产生比微调模型更合理的解释;并且Shapley Value Sampling(沙普利值采样)在生成更合理、更忠实的解释方面,始终优于注意力机制和Integrated Gradients(积分梯度)。

英文摘要:

Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the quality of attribution scores extracted from prompt-based models has not been investigated yet. In this work, we address this topic by analyzing attribution scores extracted from prompt-based models w.r.t. plausibility and faithfulness and comparing them with attribution scores extracted from fine-tuned models and large language models. In contrast to previous work, we introduce training size as another dimension into the analysis. We find that using the prompting paradigm (with either encoder-based or decoder-based models) yields more plausible explanations than fine-tuning the models in low-resource settings and Shapley Value Sampling consistently outperforms attention and Integrated Gradients in terms of leading to more plausible and faithful explanations.

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。

↑