用图增强提示构建语言模型森林，自动补全缺失数据。
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
- 构建基于双分图的提示网络，精准定位相关数据条目。
- 通过自信度加权投票融合多个语言模型输出，提升补全准确率。
- 无需微调即可在9个真实数据集上表现优异，适合医疗金融场景。
缺失数据补全在医疗、金融等领域至关重要，数据完整性直接影响分析准确性。大型语言模型（LLM）凭借海量语料训练，在数据生成方面展现潜力，但如何设计有效的零微调提示，并缓解模型输出中的偏差与不确定性仍是挑战。为此，我们提出 LLM-Forest 框架，借鉴随机森林思想，构建由少样本提示学习的多个 LLM「树」组成的「森林」，并通过基于模型自我评估的置信度加权投票聚合结果。该框架引入一种新型二分信息图，以特征和数值粒度识别高质量相关邻近条目。在9个真实世界数据集上的大量实验表明，该方法兼具有效性与高效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。