牛哥精选 · 半年

1

📝 深度技术 arXiv AI 2026-08-25

Credal Large Language Models for Semantic Commitment under Uncertainty

集合LoRA适配器构建置信区间，让大模型区分“不知道”与“不确定”，告别过度自信的胡说八道。

arXiv:2608.23244v1 Announce Type: cross Abstract: Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence.…

大模型不确定性 lora 集成学习语义承诺

2

📝 深度技术 arXiv NLP 2026-07-28

Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection

用LLM自动生成决策树集成，兼顾可解释性与鲁棒性，为错误检测任务提供新范式

arXiv:2512.07246v2 Announce Type: replace Abstract: Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data…

llm 决策树集成学习错误检测可解释ai

3

📝 深度技术 arXiv 机器学习 2026-07-17

Cross-Cluster Weighted Forests

跨簇加权森林巧妙利用数据异质性，为生物应用构建更可信的集成学习模型

arXiv:2105.07610v5 Announce Type: replace-cross Abstract: Building trustworthy machine learning algorithms for biological applications requires adapti…

cross-clus 集成学习数据异质性生物应用机器学习

4

🤖 AI·大模型 arXiv AI 2026-06-26

Tuning Language Models by Mixture-of-Depths Ensemble

大模型调优新思路：用混合深度集成技术提升语言模型性能，值得关注！

arXiv:2410.13077v2 Announce Type: replace-cross Abstract: Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for fi…

语言模型调优 mixture-of 集成学习大模型论文推荐

5

📝 深度技术 arXiv AI 2026-06-24

Ensemble Learning for Large Language Models in Text and Code Generation: A Survey

权威综述，系统梳理LLM集成学习在文本与代码生成中的方法、挑战与未来方向。

arXiv:2503.13505v3 Announce Type: replace-cross Abstract: Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for …

大语言模型集成学习文本生成代码生成综述

6

📝 深度技术 arXiv AI 2026-06-24

Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data

用LLM生成问题构建可解释的随机规则森林，从非结构化数据中预测成功，兼顾性能与可管理性。

arXiv:2505.24622v3 Announce Type: replace Abstract: Many high-stakes screening tasks require predicting rare outcomes from unstructured text, where er…

llm 随机规则森林可解释ai 非结构化数据集成学习

7

📝 深度技术 arXiv AI 2026-06-10

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

分层因果发现新范式，用LLM动态加权专家模型，提升因果推断准确性与可解释性。

arXiv:2606.10607v1 Announce Type: cross Abstract: Causal discovery aims to uncover causal structures from observational data, which is crucial for rea…

因果发现大语言模型集成学习层次化方法专家重加权

8

📝 深度技术 arXiv AI 2026-06-08

Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

仅用两个推理样本即可实现LLM自一致性？CoT+PoT集成方案，大幅提升推理效率的新突破。

arXiv:2604.17433v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large l…

llm推理自一致性 cot pot 集成学习

9

🤖 AI·大模型 arXiv AI 2026-06-03

CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery

大模型做因果发现时何时可信？这篇论文提出CauTion框架，动态评估LLM的集成信任度，提升因果推断鲁棒性。

arXiv:2606.03602v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the fundamental limitations of p…

llm 因果发现可信度集成学习人工智能安全

10

📝 深度技术 arXiv 机器学习 2026-06-01

Consolidating Rewarded Perturbations for LLM Post-Training

把后训练循环从样本空间移到权重空间，用高斯扰动采样+奖励排序集成专家，开辟LLM微调新范式。

arXiv:2605.31494v1 Announce Type: cross Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gra…

llm后训练奖励扰动权重空间高斯采样集成学习

11

📝 深度技术 arXiv 机器学习 2026-05-28

Local MDI+: Local Feature Importances for Tree-Based Models

提出Local MDI+方法，提升树模型局部特征重要性解释的准确性和可靠性

arXiv:2506.08928v2 Announce Type: replace Abstract: Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning m…

local mdi+ 特征重要性树模型随机森林可解释性

12

🤖 AI·大模型 arXiv 机器学习 2026-05-28

Soft Specialists: $\alpha$-R\'enyi Ensembles for Uncertainty-Aware LLM Post-Training

用α-Rényi集成提升LLM后训练的不确定性建模，学术前沿。

arXiv:2605.27747v1 Announce Type: cross Abstract: Existing training approaches for large language models learn a single set of parameters, based on la…

llm 不确定性量化集成学习后训练 rényi熵

13

📝 深度技术 arXiv 机器学习 2026-05-27

Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques

提出图Transformer后验建模与集成技术，实现矽肺和肺炎的精准分类，并发布新胸部X光数据集SVBCX。

arXiv:2501.00520v2 Announce Type: replace-cross Abstract: This paper presents a comprehensive study on the classification and detection of Silicosis-r…

图transform 后验建模集成学习矽肺分类胸部x光

14

🤖 AI·大模型 arXiv 机器学习 2026-05-26

ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning

基于区块链的容量感知联邦集成学习框架，专为医学影像中资源不均的医院设计。

arXiv:2605.24418v1 Announce Type: new Abstract: Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard fede…

联邦学习区块链医学影像容量感知集成学习

15

📝 深度技术 arXiv 计算机视觉 2026-05-21

FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition

将多模态大语言模型引入细粒度水果识别，通过仲裁机制实现异构集成，大幅提升准确率。

arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, …

细粒度识别 mllm 集成学习计算机视觉水果识别

16

📝 深度技术 arXiv 机器学习 2026-05-20

Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information

顶会ICML2026新研究，利用高阶信息提升LLM聚合效果，超越传统多数投票方法。

arXiv:2510.01499v2 Announce Type: replace Abstract: With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively ag…

llm 模型聚合多数投票高阶信息集成学习

17