mlsanityData to 14 Oct 2026

LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation

arXiv 2410.21520 ↗First posted 28 Oct 2024cs.LG cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Missing data imputation is a critical challenge in various domains, such as healthcare and finance, where data completeness is vital for accurate analysis. Large language models (LLMs), trained on vast corpora, have shown strong potential in data generation, making them a promising tool for data imputation. However, challenges persist in designing effective prompts for a finetuning-free process and in mitigating biases and uncertainty in LLM outputs. To address these issues, we propose a novel framework, LLM-Forest, which introduces a "forest" of few-shot prompt learning LLM "trees" with their outputs aggregated via confidence-based weighted voting based on LLM self-assessment, inspired by the ensemble learning (Random Forest). This framework is established on a new concept of bipartite information graphs to identify high-quality relevant neighboring entries with both feature and value granularity. Extensive experiments on 9 real-world datasets demonstrate the effectiveness and efficiency of LLM-Forest.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 27 of its 76 references that are in the map. First posted on arXiv 28 Oct 2024.

Builds on

27 of 76 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  6. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  8. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  9. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  10. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  11. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  12. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
15 more
  1. 2022Binding Language Models in Symbolic Languagescited by 228
  2. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  3. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 178
  4. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  5. 2020Handling Missing Data with Graph Representation Learningcited by 133
  6. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  7. 2024Large Language Model for Table Processing: A Surveycited by 52
  8. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 51
  9. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 41
  10. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoningcited by 32
  11. 2023Transformed Distribution Matching for Missing Value Imputationcited by 31
  12. 2024A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfercited by 12
  13. 2024Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Modelscited by 7
  14. 2022TableQuery: Querying tabular data with natural languagecited by 5
  15. 2024What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 12.

25 papers.

Sort:

By area:

  1. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
  2. 2026Your Group-Relative Advantage Is Biasedcited by 34
  3. 2025SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidencecited by 18
  4. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 18
  5. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 17
  6. 2024PyG-SSL: A Graph Self-Supervised Learning Toolkitcited by 14
  7. 2024Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?cited by 13
  8. 2026Real-Time Aligned Reward Model beyond Semanticscited by 13
  9. 2026Counterfactual Credit Policy Optimization for Multi-Agent Collaborationcited by 10
  10. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  11. 2025LLMBoost: Make Large Language Models Stronger with Boostingcited by 8
  12. 2025NIRVANA: Structured Pruning Reimagined for Large Language Model Compressioncited by 6
13 more
  1. 2026Weak-Driven Learning: How Weak Agents make Strong Agents Strongercited by 5
  2. 2025Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Processcited by 4
  3. 2024STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsingcited by 3
  4. 2025Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Itemscited by 2
  5. 2025How many patients could we save with LLM priors?cited by 2
  6. 2026Adaptive Robust Estimator for Multi-Agent Reinforcement Learningcited by 2
  7. 2026Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputationcited by 1
  8. 2025Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical Reasoningcited by 0
  9. 2026ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflowscited by 0
  10. 2026SafeImpute: Reliable Clinical Data Imputation via Conformal Selectioncited by 0
  11. 2026Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Modelscited by 0
  12. 2026EdgeLM: Edge Demonstrations for Language Models' Table Understandingcited by 0
  13. 2026Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learningcited by 0