arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14335cs.CLcs.AI
收藏

用于文本分析的线性可解释概念嵌入模型

Linearly-Interpretable Concept Embedding Models for Text Analysis

CENTAI Institute(CENTAI研究所)

Francesco De Santis, Philippe Bich, Gabriele Ciravegna, Pietro Barbiero, Danilo Giordano, Tania Cerquitelli

AI总结:

本文提出线性可解释概念嵌入模型(LICEM),通过结合LLM主干自动预测概念,无需概念监督即可训练,在分类准确率上超越现有可解释模型并媲美黑盒模型,同时提供更具可干预性和因果一致性的解释。

摘要:

尽管取得了成功,但大型语言模型(LLMs)仍因其缺乏可解释性而面临批评。传统的基于注意力和梯度分析的事后解释方法提供的见解有限,因为它们仅近似模型的决策过程,并且已被证明是不可靠的。出于这个原因,最近在文本领域提出了概念瓶颈模型(CBMs),以提供基于人类可理解概念的可解释预测。然而,CBMs 仍然表现出几个局限性,这是由于其架构约束限制了其表达能力,在采用非线性任务预测器时缺乏任务可解释性,并且需要广泛的注释,这对于现实世界的文本数据来说是不切实际的。在本文中,我们通过提出一种新颖的线性可解释概念嵌入模型(LICEM)来解决这些挑战,该模型超越了当前的准确率-可解释性权衡。LICEMs 的分类准确率优于现有的可解释模型,并可与黑盒模型相媲美。我们表明,我们的模型提供的解释比现有解决方案更具可干预性,并且在因果上更加一致。最后,我们表明 LICEMs 可以在不需要任何概念监督的情况下进行训练,因为在使用 LLM 主干时可以自动预测概念。

英文摘要:

Despite their success, Large-Language Models (LLMs) still face criticism due to their lack of interpretability. Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insights as they only approximate the model's decision-making processes and have been proved to be unreliable. For this reason, Concept-Bottleneck Models (CBMs) have been lately proposed in the textual field to provide interpretable predictions based on human-understandable concepts. However, CBMs still exhibit several limitations due to their architectural constraints limiting their expressivity, to the absence of task-interpretability when employing non-linear task predictors and for requiring extensive annotations that are impractical for real-world text data. In this paper, we address these challenges by proposing a novel Linearly Interpretable Concept Embedding Model (LICEM) going beyond the current accuracy-interpretability trade-off. LICEMs classification accuracy is better than existing interpretable models and matches black-box ones. We show that the explanations provided by our models are more interveneable and causally consistent with respect to existing solutions. Finally, we show that LICEMs can be trained without requiring any concept supervision, as concepts can be automatically predicted when using an LLM backbone.

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。

↑