mlsanityData to 7 Oct 2026

Cool-Fusion: Fuse Large Language Models without Training

arXiv 2407.19807 ↗First posted 29 Jul 2024cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high computational load, specifically in fine-tuning or aligning vocabularies. To address this, we propose Cool-Fusion, a simple yet effective approach that fuses the knowledge of source LLMs, which does not require training. Unlike ensemble methods, Cool-Fusion is applicable to any set of source LLMs that have different vocabularies. To overcome the vocabulary discrepancies among LLMs, we ensemble LLMs on text level, allowing them to rerank the generated texts by each other with different granularities. Extensive experiments have been conducted across a variety of benchmark datasets. On GSM8K, Cool-Fusion increases accuracy from three strong source LLMs by a significant margin of 17.4%.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

22 of 36 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  8. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  9. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  10. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  11. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  12. 2018CoQA: A Conversational Question Answering Challengecited by 674
10 more
  1. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  2. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  3. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  4. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  5. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 249
  6. 2022SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarizationcited by 61
  7. 2024Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimizationcited by 56
  8. 2024Bridging the Gap between Different Vocabularies for LLM Ensemblecited by 44
  9. 2024LLM Augmented LLMs: Expanding Capabilities through Compositioncited by 35
  10. 2023An Empirical Study of Translation Hypothesis Ensembling with Large Language Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 3.

12 papers.

  1. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
  2. 2024Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoningcited by 38
  3. 2024Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensemblingcited by 27
  4. 2025Harnessing Consistency for Robust Test-Time LLM Ensemblecited by 10
  5. 2025Sampling from Your Language Model One Byte at a Timecited by 7
  6. 2025Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Processcited by 4
  7. 2026AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMscited by 4
  8. 2025When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensemblingcited by 3
  9. 2024Exploring Model Kinship for Merging Large Language Modelscited by 2
  10. 2025Lossless Vocabulary Reduction for Auto-Regressive Language Modelscited by 2
  11. 2026Ensembling Language Models with Sequential Monte Carlocited by 2
  12. 2026Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaborationcited by 0