English(EN) Imputation of Public Opinion Data with Large Language Models

大型语言模型在调查数据插补方面难以超越统计方法

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

一篇新的arXiv论文探讨了使用大型语言模型（LLMs）对公众意见调查数据中的缺失值进行插补。该研究评估了六种开源LLMs的84种上下文学习配置，发现虽然LLMs可以改进零样本角色提示，但充其量只能与MICE PMM和TabPFN等传统统计方法相媲美。研究强调，LLM插补的计算成本显著更高，并且对调查主题敏感，而常见的LLM预测指标并不能可靠地指示插补质量，这突显了进行适合特定任务的评估的必要性。 AI

影响对于调查数据插补而言，LLMs尚未成为优于既有统计方法的选择，需要针对特定任务进行仔细评估。

排序理由在arXiv上发表的研究论文，详细介绍了LLM在数据插补方面的能力。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 在arXiv上发表的研究论文，详细介绍了LLM在数据插补方面的能力。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Tobias Holtdirk, Georg Ahnert, Joseph W Sakshaug, Anna-Carolina Haensch · 2026-11-02 05:00

Imputation of Public Opinion Data with Large Language Models

arXiv:2606.09351v2 Announce Type: replace Abstract: Large language models (LLMs) are widely evaluated as simulators of survey responses, yet applied survey research mostly faces item nonresponse. Imputation fills in those missing values to restore the overall structure of a parti…

本文如何被排名

报道来源 [1]

Imputation of Public Opinion Data with Large Language Models

相关实体

相关话题