Saved in:
Bibliographic Details
Main Authors: Yang, Yi, Duan, Hanyu, Liu, Jiaxin, Tam, Kar Yan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.12722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914952719106048
author Yang, Yi
Duan, Hanyu
Liu, Jiaxin
Tam, Kar Yan
author_facet Yang, Yi
Duan, Hanyu
Liu, Jiaxin
Tam, Kar Yan
contents The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12722
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research
Yang, Yi
Duan, Hanyu
Liu, Jiaxin
Tam, Kar Yan
Computation and Language
The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.
title LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research
topic Computation and Language
url https://arxiv.org/abs/2409.12722