Rethinking LLM Ensembling from the Perspective of Mixture Models

• URL: http://arxiv.org/abs/2605.00419v1
• Date: Fri, 01 May 2026 05:31:18 GMT
• Title: Rethinking LLM Ensembling from the Perspective of Mixture Models
• Abstract summary: We propose the Mixture-like Ensemble (ME) for large language models (LLMs)<n>ME is mathematically equivalent to sampling from the ensemble distribution, but requires invoking only one model, making it 1.78x-2.68x faster than conventional ensemble.<n>Our findings open new avenues for efficient LLM ensembling and motivate further exploration of token-level routing strategies.
• Score: 41.97945120072535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea has been naturally extended to large language models (LLMs), yielding improved performance but incurring substantial computational cost. This inefficiency stems from directly applying conventional ensemble implementation to LLMs, which require a separate forward pass for each model to explicitly compute the ensemble distribution. In this paper, we propose the Mixture-model-like Ensemble (ME). By reinterpreting the ensemble as a mixture model, ME stochastically selects a single model at each step to generate the next token, thereby avoiding the need to explicitly compute the full ensemble distribution. ME is mathematically equivalent to sampling from the ensemble distribution, but requires invoking only one model, making it 1.78x-2.68x faster than conventional ensemble. Furthermore, this perspective connects LLM ensembling and token-level routing methods, suggesting that LLM ensembling is a special case of routing methods. Our findings open new avenues for efficient LLM ensembling and motivate further exploration of token-level routing strategies for LLMs. Our code is available at https://github.com/jialefu/Mixture-model-like-Ensemble/.

Related papers

• Unlocking Lossless Speedups in LLMs via Discrete Diffusion [67.4336730000437]
  Large Language Models (LLMs) owe much of their success to next-token prediction (NTP)<n>We introduce diffusion-augmented LLMs, a new class of models that defines an AR model distribution.<n>We decouple the parameters of these models into two sets: AR weights, trained using the standard NTP objective, and lightweight diffusion weights, trained to generate multiple tokens simultaneously.
  arXiv  Detail & Related papers  (2026-09-03T15:48:43Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Universal Model Routing for Efficient LLM Inference [69.86195589350264]
  Model routing is a technique for reducing the inference cost of large language models (LLMs)<n>We propose UniRoute, a new approach to the problem of dynamic routing, where new, previously unobserved LLMs are available at test time.<n>We show that these are estimates of a theoretically optimal routing rule, and quantify their errors via an excess risk bound.
  arXiv  Detail & Related papers  (2025-02-12T20:30:28Z)
• SpecFuse: Ensembling Large Language Models via Next-Segment Prediction [42.28242821924789]
  SpecFuse is an ensemble framework that outputs a fused result by iteratively producing the next segment through collaboration among LLMs.<n>The top-ranked segment is then broadcast to all LLMs, encouraging them to generate higher-quality segments in the next round.<n>To conserve computational resources, we propose a model exit mechanism that dynamically excludes models exhibiting poor performance in previous rounds.
  arXiv  Detail & Related papers  (2024-12-10T10:27:41Z)
• Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
  This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline.<n>We benchmark existing scaling techniques, especially selective merging, and variants of mixture.<n>We then formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo.<n>Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters.
  arXiv  Detail & Related papers  (2024-10-07T15:55:55Z)
• No Need to Talk: Asynchronous Mixture of Language Models [25.3581396758015]
  Smalltalk LM is an innovative method for training a mixture of language models in an almost asynchronous manner.<n>At inference, a lightweight router directs a given sequence to a single expert, according to a short prefix.<n>Experiments on language modeling demonstrate that SMALLTALK LM achieves significantly lower perplexity than dense model baselines.
  arXiv  Detail & Related papers  (2024-10-04T15:50:10Z)
• Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration [39.35476224845088]
  Large language models (LLMs) exhibit complementary strengths in various tasks, motivating the research of LLM ensembling. We propose a training-free ensemble framework DeePEn, fusing the informative probability distributions yielded by different LLMs at each decoding step.
  arXiv  Detail & Related papers  (2024-04-19T08:52:22Z)
• Knowledge Fusion of Large Language Models [73.28202188100646]
  This paper introduces the notion of knowledge fusion for large language models (LLMs) We externalize their collective knowledge and unique strengths, thereby elevating the capabilities of the target model beyond those of any individual source LLM. Our findings confirm that the fusion of LLMs can improve the performance of the target model across a range of capabilities such as reasoning, commonsense, and code generation.
  arXiv  Detail & Related papers  (2024-01-19T05:02:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.