Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms

Arthur Dantas Mangussi, Ricardo Cardoso Pereira, Ana Carolina Lorena, Pedro Henriques Abreu

Abstract

Data imputation is a cornerstone technique for handling missing values in real-world datasets, which are often plagued by missingness. Despite recent progress, prior studies on Large Language Models-based imputation remain limited by scalability challenges, restricted cross-model comparisons, and evaluations conducted on small or domain-specific datasets. Furthermore, heterogeneous experimental protocols and inconsistent treatment of missingness mechanisms (MCAR, MAR, and MNAR) hinder systematic benchmarking across methods. This work investigates the robustness of Large Language Models for missing data imputation in tabular datasets using a zero-shot prompt engineering approach. To this end, we present a comprehensive benchmarking study comparing five widely used LLMs against six state-of-the-art imputation baselines. The experimental design evaluates these methods across 29 datasets (including nine synthetic datasets) under MCAR, MAR, and MNAR mechanisms, with missing rates of up to 20\%. The results demonstrate that leading LLMs, particularly Gemini 3.0 Flash and Claude 4.5 Sonnet, consistently achieve superior performance on real-world open-source datasets compared to traditional methods. However, this advantage appears to be closely tied to the models' prior exposure to domain-specific patterns learned during pre-training on internet-scale corpora. In contrast, on synthetic datasets, traditional methods such as MICE outperform LLMs, suggesting that LLM effectiveness is driven by semantic context rather than purely statistical reconstruction. Furthermore, we identify a clear trade-off: while LLMs excel in imputation quality, they incur significantly higher computational time and monetary costs. Overall, this study provides a large-scale comparative analysis, positioning LLMs as promising semantics-driven imputers for complex tabular data.

Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms

Abstract

Data imputation is a cornerstone technique for handling missing values in real-world datasets, which are often plagued by missingness. Despite recent progress, prior studies on Large Language Models-based imputation remain limited by scalability challenges, restricted cross-model comparisons, and evaluations conducted on small or domain-specific datasets. Furthermore, heterogeneous experimental protocols and inconsistent treatment of missingness mechanisms (MCAR, MAR, and MNAR) hinder systematic benchmarking across methods. This work investigates the robustness of Large Language Models for missing data imputation in tabular datasets using a zero-shot prompt engineering approach. To this end, we present a comprehensive benchmarking study comparing five widely used LLMs against six state-of-the-art imputation baselines. The experimental design evaluates these methods across 29 datasets (including nine synthetic datasets) under MCAR, MAR, and MNAR mechanisms, with missing rates of up to 20\%. The results demonstrate that leading LLMs, particularly Gemini 3.0 Flash and Claude 4.5 Sonnet, consistently achieve superior performance on real-world open-source datasets compared to traditional methods. However, this advantage appears to be closely tied to the models' prior exposure to domain-specific patterns learned during pre-training on internet-scale corpora. In contrast, on synthetic datasets, traditional methods such as MICE outperform LLMs, suggesting that LLM effectiveness is driven by semantic context rather than purely statistical reconstruction. Furthermore, we identify a clear trade-off: while LLMs excel in imputation quality, they incur significantly higher computational time and monetary costs. Overall, this study provides a large-scale comparative analysis, positioning LLMs as promising semantics-driven imputers for complex tabular data.
Paper Structure (19 sections, 1 equation, 4 figures, 9 tables)

This paper contains 19 sections, 1 equation, 4 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Prompt-Based Direct Imputation
  4. Hybrid Architectures Integrating LLMs with Structural Modules
  5. Context-Enrichment and Dual-Phase Frameworks
  6. Transformer-Based Models for Tabular Imputation
  7. Limitations of Existing Literature
  8. Methodology
  9. Data Collection
  10. Imputation Process
  11. Prompt Construction and Batch Strategy
  12. Results and Discussion
  13. Overall Performance
  14. Degradation Under Increasing Missing Rates
  15. LLM-Based vs. Traditional Imputation
  16. ...and 4 more sections

Figures (4)

  • Figure 1: Overview of methodology applied in this work.
  • Figure 2: Illustration of the complete prompt structure used to perform data imputation via prompt engineering.
  • Figure 3: Density plots of the Normalized Root Mean Square Error results obtained for each imputation strategy. The analysis is presented by missing data mechanisms. The average NRMSE for each setting is also displayed.
  • Figure 4: NRMSE vs. computational time across imputation methods. Each point corresponds to a dataset. The x-axis reports imputation accuracy (NRMSE), while the y-axis shows runtime in seconds (log scale). The figure highlights the trade-off between predictive performance and computational cost across LLM-based and traditional imputation approaches with Pareto frontier.