Revealing economic facts: LLMs know more than they say
We investigate whether the hidden states of large language models (LLMs) can be used to estimate and impute economic and financial statistics. Focusing on county-level (e.g. unemployment) and firm-level (e.g. total assets) variables, we show that a simple linear model trained on the hidden states of open-source LLMs outperforms the models' text outputs. This suggests that hidden states capture richer economic information than the responses of the LLMs reveal directly. A learning curve analysis indicates that only a few dozen labelled examples are sufficient for training. We also propose a transfer learning method that improves estimation accuracy without requiring any labelled data for the target variable. Finally, we demonstrate the practical utility of hidden-state representations in super-resolution and data imputation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
ImputationSuper-ResolutionTransfer LearningSimilar Papers 제목 키워드 기반
AI as Decision-Maker: Ethics and Risk Preferences of LLMs
Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We ana…
Decision MakingEthicsExposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an …
knowledge editingTemporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN
Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data. Two recent studies with accompanying datasets report opposite conclusions on whethe…
Scaling Laws for Fact Memorization of Large Language Models
Fact knowledge memorization is crucial for Large Language Models (LLM) to generate factual and reliable responses. However, the behaviors of LLM fact memorization remain under-explored. In this paper, we analyze the scal…
MemorizationAlgebraic Properties of Blackwell's Order and A Cardinal Measure of Informativeness
I establish a translation invariance property of the Blackwell order over experiments, show that garbling experiments bring them closer together, and use these facts to define a cardinal measure of informativeness. Exper…
InformativenessTranslation