# SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models

arXiv: https://arxiv.org/abs/2408.08545 · HTML: https://mlsanity.com/paper/2408.08545/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Large Language Model Routing with Benchmark Datasets](https://mlsanity.com/paper/2309.15789/) (2023)
- [Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning](https://mlsanity.com/paper/1811.12808/) (2018)
- [SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization](https://mlsanity.com/paper/2106.01890/) (2021)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization](https://mlsanity.com/paper/2203.06569/) (2022)
- [Fast Structured Decoding for Sequence Models](https://mlsanity.com/paper/1910.11555/) (2019)
- [Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing](https://mlsanity.com/paper/2405.00467/) (2024)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)
- [Chain of Thought Prompting Elicits Knowledge Augmentation](https://mlsanity.com/paper/2307.01640/) (2023)
- [What Makes Math Word Problems Challenging for LLMs?](https://mlsanity.com/paper/2403.11369/) (2024)
- [Tree Prompting: Efficient Task Adaptation without Fine-Tuning](https://mlsanity.com/paper/2310.14034/) (2023)
- [Confidence-aware Contrastive Learning for Selective Classification](https://mlsanity.com/paper/2406.04745/) (2024)
- [Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases](https://mlsanity.com/paper/2403.16396/) (2024)

## Built on by (most cited first, 8 of 8)

- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs](https://mlsanity.com/paper/2507.08960/) (2025)
- [LLM Routing with Dueling Feedback](https://mlsanity.com/paper/2510.00841/) (2025)
- [On Calibration of Large Language Models: From Response To Capability](https://mlsanity.com/paper/2602.13540/) (2026)
- [Enhancing LLM Metacognition via Cognitive Pairwise Training](https://mlsanity.com/paper/2606.00869/) (2026)
- [Software Performance Engineering for Foundation Model-Powered Software](https://mlsanity.com/paper/2411.09580/) (2024)
- [ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge](https://mlsanity.com/paper/2507.06011/) (2025)
- [CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering](https://mlsanity.com/paper/2507.22937/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have been widely adopted due to their remarkable performance across various applications, driving the accelerated development of a large number of diverse models. However, these individual LLMs show limitations in generalization and performance on complex tasks due to inherent training biases, model size constraints, and the quality or diversity of pre-training datasets. A promising direction is to efficiently harness the diverse capabilities of LLMs to overcome these individual limitations. To address these limitations, we introduce a novel LLM selection algorithm called SelectLLM, which efficiently directs input queries to the most suitable subset of LLMs from a large pool, ensuring that the selected models collectively provide accurate responses. SelectLLM employs a multi-label classifier and policy based on the classifier's predictions and confidence scores in selecting an optimal, query-aware, and lightweight subset of LLMs. Our findings indicate that the proposed model outperforms existing ensemble-based baselines and achieves competitive performance with similarly sized top-performing LLMs while maintaining efficiency. Specifically, it achieves a huge reduction in inference latency on two challenging reasoning benchmarks: 13% on GSM8K and 70% on MMLU, compared to the top-performing baseline. Also, we establish a theoretical upper bound by an Oracle with LLMs and perform an in-depth linguistic analysis to understand the performance gap between the Oracle and SelectLLM.