大模型能模仿人类对通胀的感知，但缺乏稳定通胀认知。
Inflation Attitudes of Large Language Models
- 用英国通胀调查数据对比GPT-3.5-turbo输出，模拟真实人群反应。
- 短期预测与官方数据和民众调查高度一致，但对整体通胀无稳定判断。
- 对食品通胀敏感度类似人类，适合用于社会科学研究与问卷设计。
本文研究大语言模型（如GPT-3.5-turbo）基于宏观经济价格信号形成通胀感知与预期的能力。通过与英国央行通胀态度调查（IAS）的住户数据及官方统计对比，采用准实验设计，利用GPT训练截止于2021年9月这一时间点，使其无法知晓此后英国通胀飙升。结果显示，GPT在短期预测上与调查均值和官方数据高度一致；在细分层面，其对收入、住房类型、社会阶层的通胀感知也复现了居民的典型规律。通过适用于合成调查场景的Shapley值分解，发现模型对食品通胀信息尤为敏感，接近人类反应。但整体而言，其对消费者价格通胀缺乏一致性认知。该方法可推广至评估多模型行为、比较不同模型表现或辅助社会科学研究中的问卷设计。
原文摘要 · Abstract (English)
This paper investigates the ability of Large Language Models (LLMs), specifically GPT-3.5-turbo (GPT), to form inflation perceptions and expectations based on macroeconomic price signals. We compare the LLM's output to household survey data and official statistics, mimicking the information set and demographic characteristics of the Bank of England's Inflation Attitudes Survey (IAS). Our quasi-experimental design exploits the timing of GPT's training cut-off in September 2021 which means it has no knowledge of the subsequent UK inflation surge. We find that GPT tracks aggregate survey projections and official statistics at short horizons. At a disaggregated level, GPT replicates key empirical regularities of households' inflation perceptions, particularly for income, housing tenure, and social class. A novel Shapley value decomposition of LLM outputs suited for the synthetic survey setting provides well-defined insights into the drivers of model outputs linked to prompt content. We find that GPT demonstrates a heightened sensitivity to food inflation information similar to that of human respondents. However, we also find that it lacks a consistent model of consumer price inflation. More generally, our approach could be used to evaluate the behaviour of LLMs for use in the social sciences, to compare different models, or to assist in survey design.
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。