推理还是背诵？通过反事实任务探索语言模型的能力与局限
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
AI总结：
本文通过11项反事实任务变体评估语言模型，发现其性能虽非零但较默认条件显著下降，表明模型兼具抽象推理与狭窄不可迁移的程序化解题能力，呼吁更谨慎地解读模型表现。
摘要：
近期语言模型在广泛任务上的出色表现表明它们具有一定程度的抽象推理能力。这些能力是通用的、可迁移的，还是专门针对预训练期间所见特定任务的？为了厘清这些效应，我们提出一个基于“反事实”任务变体的评估框架，这些变体偏离了标准任务所依赖的默认假设。在包含11项任务的套件中，我们观察到模型在反事实变体上表现出不可忽视的性能，但发现与默认条件相比，性能仍出现大幅且一致的下降。这表明，尽管当前语言模型在一定程度上可能具备抽象的任务解决能力，但它们往往也依赖狭窄的、不可迁移的程序来完成任务。这些结果促使我们对语言模型性能进行更谨慎的解读，以区分行为中的这些不同方面。
英文摘要：
The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during pretraining? To disentangle these effects, we propose an evaluation framework based on "counterfactual" task variants that deviate from the default assumptions underlying standard tasks. Across a suite of 11 tasks, we observe nontrivial performance on the counterfactual variants, but nevertheless find that performance substantially and consistently degrades compared to the default conditions. This suggests that while current LMs may possess abstract task-solving skills to an extent, they often also rely on narrow, non-transferable procedures for task-solving. These results motivate a more careful interpretation of language model performance that teases apart these aspects of behavior.
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。
