PulseAugur
EN
LIVE 10:44:49

LLMs simulate survey respondents with 52% accuracy in new study

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new method called "silicon sampling" that uses large language models (LLMs) to simulate human survey respondents. This approach aims to augment traditional survey research by predicting individual responses to unseen questions. A study using the Taiwan Election and Democratization Study (TEDS) 2024 data found that zero-shot LLMs achieved 52% accuracy, closely approaching supervised machine learning models. AI

IMPACT This research suggests LLMs can effectively simulate human survey respondents, potentially improving data collection efficiency and scope.

RANK_REASON The cluster contains an academic paper detailing a new methodology for using LLMs in survey research.

Read on arXiv cs.MA (Multiagent) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

LLMs simulate survey respondents with 52% accuracy in new study

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Frank Cheng-shan Liu, I-Ling Cheng, Yihuang Kang ·

    Silicon Sampling via Cross-Survey Transfer

    arXiv:2607.03091v1 Announce Type: new Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons ra…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Yihuang Kang ·

    Silicon Sampling via Cross-Survey Transfer

    Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons rather than individual-level prediction, which ris…

RELATED ENTITIES

RELATED TOPICS