Ensemble Diversity

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 16

All topics

Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
Sep 29, 2026Liangyu Teng, Hengsong Liu, Juncen Guo +4Language Model Ensembles Ensemble Diversity
Fudan Institute on Networking Systems of AI
CORE-STACK+: Meta-Learning for Deep Stacked Generalization
Sep 22, 2026Noor Islam S. MohammadEnsemble Learning Meta-Learning
Department of Computer Science Istanbul Technical University Maslak, Istanbul 34469, TR
How Many Humans Are 32 LLM Judges Worth?
Sep 18, 2026Chao Li, Yingying Yu, Yunfeng LiAnnotator Disagreement LLM-as-a-Judge
Tsinghua University · University College London · Hebei University of Economics and Business
Breaking Diversity Collapse in Spiking Pseudo-Ensembles for Efficient OOD Detection in Remote Sensing
Aug 2, 2026Srinivas Anumasa, Rushi Shah, Qiran Zou +1Efficient Neural Network Inference Ensemble Learning
National University of Singapore
Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct
Jul 31, 2026Mario Vega-Barbas, Lidia Mora-Valenciano, Iván Pau +2Language Model Ensembles Clinical Language Model Evaluation
ETSIS de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Madrid, Spain · Independent Researcher, Guadalajara, Spain · Department of Clinical Science, Intervention and Technology, Karolinska Institutet, Huddinge, Stockholm, Sweden +4
Surrogate assisted diversity estimation in neural ensemble search
Jul 29, 2026Alexandr Udeneev, Petr Babkin, Oleg BakhteevSurrogate-Assisted Optimization Neural Architecture Search
Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
Jul 26, 2026Mihai Suteu, Ovidiu SerbanEnsemble Learning Ensemble Diversity
Data Science Institute, Imperial College London
Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles
Jul 22, 2026Donghwan KimLLM Evaluation Language Model Ensembles
Aidentyx Inc., San Jose, CA, USA
Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift
Jul 19, 2026Junade AliEnsemble Learning Language Model Ensembles
Defence and National Security Programme The Alan Turing Institute London, United Kingdom
Ensemble Diversity Optimization for Subjective Supervision
Jul 9, 2026Xia Cui, Ziyi Huang, N. R. AbeynayakeAnnotator Disagreement Ensemble Learning
School of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK. · School of Computer Science, Hubei University, Wuhan, China.
Diversity is the Strength of the AI Crowd
Jun 29, 2026Matthew Aitchison, Scott Jeen, Toby Shevlane +1Forecasting Benchmarks Language Model Ensembles
1Mantic Technologies, London, UK.
Reducing Learner Redundancy in Boosting via Residual Orthogonalization
Jun 16, 2026Ye Su, Jipeng Guo, Yong Liu +5Ensemble Learning Residual Learning
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China · College of Information Science and Technology, Beijing University of Chemical Technology,2026 Beijing 100029, China · Gaoling School of Artificial Intelligence, Renmin University of China, Beijing 100872, China +2
Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
May 29, 2026Yijie Tong, Yifan Hou, Shaobo Cui +2VLM Evaluation Vision-Language Models
ETH Zürich · Shanghai Jiao Tong University · EPFL
Residual Skill Optimization for Text-to-SQL Ensembles
May 20, 2026Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant +8Text-to-SQL Agent Skill Learning
University of California, San Diego · 2Snowflake AI Research
Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
May 18, 2026Aditya Tanna, Yash Desai, Pratinav Seth +3Tabular Foundation Models Ensemble Learning
Lexsi Labs
LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning
May 14, 2026Changryeol Choi, Hyewon Park, Yujin Kwon +1Ensemble Learning Low-Rank Adaptation
CJ Logistics

Sep 29, 2026, cs.CLJ/K move · Enter open · S save

Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection

Liangyu Teng, Hengsong Liu, Juncen Guo, Jingyu Zhang+3

Fudan Institute on Networking Systems of AI

Language Model Ensembles Ensemble Diversity Multi-LLM Collaboration

Open paper AskPDF arXiv

The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive differences. Although heterogeneous teaming is often observed to be effective in practice, existing approaches lack complementarity metrics that are computable, interpretable, and optimizable, leaving team composition to rely on heuristics. We propose a heterogeneity-driven team selection framework that performs offline profiling to characterize individual capability along with two complementary signals: one captures decorrelation in error patterns to reduce co-failures, while the other measures divergence in predictive behavior to capture strategy diversity. We formulate team selection as a standardized quality--complementarity combinatorial objective and apply an efficient greedy search to select a small team from a candidate pool. Experiments across multiple benchmarks demonstrate that our framework consistently outperforms quality-only baselines under controlled candidate pools and team sizes, establishing reusable selection principles for multi-LLM systems.

Momentum

Related topics

Latest papers 16