Lune

ACL Findings2025

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

Xinrui He, Yikun Ban, Jiaru Zou, Tianxin Wei, Curtiss B. Cook, Jingrui He

Abstract

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 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

11 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Does Your Reasoning Model Implicitly Know When to Stop Thinking? cites Real-Time Aligned Reward Model beyond Semantics
  • Large Language Models Are Zero-Shot Time Series Forecasters cites Language Models are Few-Shot Learners
  • Large Language Models Are Zero-Shot Time Series Forecasters cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Real-Time Aligned Reward Model beyond Semantics cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers11

  1. ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMsJiaru Zou, Ling Yang, Jingwen Gu, Jiahao Qiu et al.NeurIPS 2025 · 51 citations
  2. Does Your Reasoning Model Implicitly Know When to Stop Thinking?Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng et al.ICML 2026 · 21 citations
  3. Real-Time Aligned Reward Model beyond SemanticsZixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng et al.ICML 2026 · 18 citations
  4. Adaptive Batch-Wise Sample Scheduling for Direct Preference OptimizationZixuan Huang, Yikun Ban, Lean Fu, Xiaojie Li et al.NeurIPS 2025 · 14 citations
  5. FeDecider: An LLM-Based Framework for Federated Cross-Domain RecommendationXinrui He, Ting-Wei Li, Tianxin Wei, Xuying Ning et al.WWW 2026 · 2 citations

Builds on16

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  3. Large Language Models Are Zero-Shot Time Series ForecastersNate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon WilsonNeurIPS 2023 · 898 citations
  4. TaBERT: Pretraining for Joint Understanding of Textual and Tabular DataPengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian RiedelACL 2020 · 417 citations
  5. Handling Missing Data with Graph Representation LearningJiaxuan You, Xiaobai Ma, Daisy Yi Ding, Mykel J. Kochenderfer et al.NeurIPS 2020 · 274 citations

Related papers

  1. Language Models are Weak LearnersHariharan Manikandan, Yiding Jiang, J. Zico KolterNeurIPS 2023 · 32 citations
  2. Data Imputation with Limited Data Redundancy Using Data LakesChenyu Yang, Yuyu Luo, Chuanxuan Cui, Ju Fan et al.VLDB 2025 · 9 citations
  3. OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model PromptingXukai Liu, Ye Liu, Kai Zhang, Kehang Wang et al.EMNLP 2024 · 7 citations
  4. On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message PassingJianmin Wang, Kai Wang, Ying Zhang, Wenjie Zhang et al.VLDB 2025 · 15 citations
  5. Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed GraphsJianxiang Yu, Yuxiang Ren, Chenghua Gong, Jiaqi Tan et al.AAAI 2025 · 32 citations
Dusk over the sea between two cliffs drawn in fine vertical lines