让语言模型模仿人类阅读习惯，提升认知建模能力。
Reverse-Engineering the Reader
- 用人类阅读时间数据微调语言模型，通过预测突兀度来优化认知匹配。
- 模型在预测人类阅读时长上表现更好，但下游任务性能下降。
- 首次证明调整心理测量对齐可主动引发模型性能与认知拟合的权衡。
以往研究多探索语言模型能否作为人类认知的有用模型，本文反其道而行之：通过将语言模型与人类心理测量数据对齐，直接优化其作为认知模型的有效性。我们提出一种新对齐方法，微调语言模型以隐式优化线性回归器参数，该回归器基于模型自身的突兀度估计，直接预测人类在上下文中的阅读时间（如音素、词素或词）。以词为测试案例，在多个模型规模和数据集上评估发现，该方法显著提升了语言模型的心理测量预测能力。然而，我们观察到心理测量能力与模型在下游NLP任务的表现及保留测试数据上的困惑度之间存在负相关关系。尽管此趋势早有报道（Oh et al., 2022; Shain et al., 2024），但本研究首次通过操纵模型与心理测量数据的对齐程度，主动诱导出这一现象。
原文摘要 · Abstract (English)
Numerous previous studies have sought to determine to what extent language models, pretrained on natural language text, can serve as useful models of human cognition. In this paper, we are interested in the opposite question: whether we can directly optimize a language model to be a useful cognitive model by aligning it to human psychometric data. To achieve this, we introduce a novel alignment technique in which we fine-tune a language model to implicitly optimize the parameters of a linear regressor that directly predicts humans' reading times of in-context linguistic units, e.g., phonemes, morphemes, or words, using surprisal estimates derived from the language model. Using words as a test case, we evaluate our technique across multiple model sizes and datasets and find that it improves language models' psychometric predictive power. However, we find an inverse relationship between psychometric power and a model's performance on downstream NLP tasks as well as its perplexity on held-out test data. While this latter trend has been observed before (Oh et al., 2022; Shain et al., 2024), we are the first to induce it by manipulating a model's alignment to psychometric data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。