在大型語言模型時代重新思考可解釋性

Rethinking Interpretability in the Era of Large Language Models

January 30, 2024

作者: Chandan Singh, Jeevana Priya Inala, Michel Galley, Rich Caruana, Jianfeng Gao

cs.AI

摘要

在過去十年中，可解釋機器學習作為一個引人關注的領域迅速蓬勃發展，這是由日益增長的大型數據集和深度神經網絡的興起所推動的。與此同時，大型語言模型（LLMs）展示了在各種任務中的卓越能力，為重新思考可解釋機器學習中的機遇提供了機會。值得注意的是，以自然語言解釋的能力使得LLMs能夠擴展可以提供給人類的規模和複雜性的模式。然而，這些新能力也帶來了新的挑戰，如虛構的解釋和巨大的計算成本。 在這篇立場論文中，我們首先回顧了評估新興LLM解釋領域的現有方法（既解釋LLMs又使用LLMs進行解釋）。我們主張，儘管存在一些限制，LLMs有機會通過更富有野心的範疇重新定義可解釋性，涵蓋眾多應用，包括審計LLMs本身。我們強調了LLM解釋的兩個新興研究重點：使用LLMs直接分析新數據集和生成互動式解釋。

English

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks, offering a chance to rethink opportunities in interpretable machine learning. Notably, the capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. However, these new capabilities raise new challenges, such as hallucinated explanations and immense computational costs. In this position paper, we start by reviewing existing methods to evaluate the emerging field of LLM interpretation (both interpreting LLMs and using LLMs for explanation). We contend that, despite their limitations, LLMs hold the opportunity to redefine interpretability with a more ambitious scope across many applications, including in auditing LLMs themselves. We highlight two emerging research priorities for LLM interpretation: using LLMs to directly analyze new datasets and to generate interactive explanations.