# SpecFuse: Ensembling Large Language Models via Next-Segment Prediction

arXiv: https://arxiv.org/abs/2412.07380 · HTML: https://mlsanity.com/paper/2412.07380/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation](https://mlsanity.com/paper/2305.09860/) (2023)
- [Bridging the Gap between Different Vocabularies for LLM Ensemble](https://mlsanity.com/paper/2404.09492/) (2024)
- [Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling](https://mlsanity.com/paper/2406.12585/) (2024)
- [Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling](https://mlsanity.com/paper/2410.03777/) (2024)
- [Nudging: Inference-time Alignment of LLMs via Guided Decoding](https://mlsanity.com/paper/2410.09300/) (2024)

## Built on by (most cited first, 6 of 6)

- [Harnessing Consistency for Robust Test-Time LLM Ensemble](https://mlsanity.com/paper/2510.13855/) (2025)
- [RLAE: Reinforcement Learning-Assisted Ensemble for LLMs](https://mlsanity.com/paper/2506.00439/) (2025)
- [Sampling from Your Language Model One Byte at a Time](https://mlsanity.com/paper/2506.14123/) (2025)
- [AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs](https://mlsanity.com/paper/2601.06022/) (2026)
- [Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation](https://mlsanity.com/paper/2606.18844/) (2026)
- [Reasoning-Intensive Regression](https://mlsanity.com/paper/2508.21762/) (2025)

## Abstract (arXiv)

Ensembles of generative large language models (LLMs) are a promising way to compensate for individual model limitations, integrating the strengths of different LLMs. Existing LLM ensemble methods, however, face limitations such as first-token delay and challenges in long-range semantic collaboration between models, Moreover, they typically assume equal voting weights for all models during ensemble, ignoring task-specific performance differences among models. In this work, we propose SpecEM, a training-free, plug-and-play LLM ensemble framework that dynamically adjusts each model's model contribution in real time based on task performance. Inspired by speculative decoding, SpecEM iteratively performs drafting and verification, allowing models to collaborate semantically at the segment level for integrated output. Furthermore, we introduce an online feedback mechanism with multiplicative weight updates, where each model's voting weight is adjusted on-the-fly according to how often it outperforms others during verification stage, ensuring that stronger models exert greater influence during ensembling. Experimental results on five LLM families (ranging from 7B to 72B parameters) and six benchmark datasets, spanning open-domain instruction following, reasoning, commonsense, demonstrate consistent performance improvements compared to state-of-the-art LLM ensemble methods. Our code is available at https://github.com/lvbotenbest/SpecEM.