paper-with-me

홈 › Papers

Revealing economic facts: LLMs know more than they say

2025-05-13 · Marcus Buckmann, Quynh Anh Nguyen, Edward Hill

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.

📄 PDF Abstract BibTeX arXiv:2505.08662

Code (0)

등록된 구현이 없습니다.

Tasks

ImputationSuper-ResolutionTransfer Learning

Similar Papers 제목 키워드 기반

AI as Decision-Maker: Ethics and Risk Preferences of LLMs

2024-06-03 · Shumiao Ouyang, Hayong Yun, Xingjian Zheng

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 MakingEthics

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

2026-06-22 · Advik Raj Basani, Anshuman Chhabra arxiv

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 editing

Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN

2026-03-16 · Ritajit Dey, Iadh Ounis, Graham McDonald, Yashar Moshfeghi arxiv

Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data.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

2024-06-22 · Xingyu Lu, Xiaonan Li, Qinyuan Cheng, Kai Ding 외

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…

Memorization

Algebraic Properties of Blackwell's Order and A Cardinal Measure of Informativeness

2021-10-21 · Andrew Kosenko

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