Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation

• URL: http://arxiv.org/abs/2510.14915v1
• Date: Thu, 16 Oct 2025 17:30:28 GMT
• Title: Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation
• Authors: Xujun Peng, Anoop Kumar, Jingyu Wu, Parker Glenn, Daben Liu,
• Abstract summary: Large Language Models (LLMs) generate accurate and reliable responses grounded in retrieved context.<n>LLMs often generate inconsistent outputs for semantically equivalent inputs.<n>We propose a new approach combining systematic synthetic data generation, triplet loss for better embeddings, and a novel layer-wise model merging approach.
• Score: 8.340691940980834
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) systems leverage Large Language Models (LLMs) to generate accurate and reliable responses that are grounded in retrieved context. However, LLMs often generate inconsistent outputs for semantically equivalent inputs, a problem compounded by the scarcity of consistency-focused training data and the limitations of current fine-tuning techniques in enhancing output consistency. We propose a new approach combining systematic synthetic data generation, triplet loss for better embeddings, and a novel layer-wise model merging approach. Using consistency-aware weights derived from intermediate layer activations, our method effectively integrates knowledge from specialized models. Experimental results how that our merged model significantly enhances output consistency, achieving a ~47.5\% improvement in response similarity over the baseline, thus offering a practical solution for increasing the reliability of an industrial RAG system.

Related papers

• Harnessing Consistency for Robust Test-Time LLM Ensemble [88.55393815158608]
  CoRE is a plug-and-play technique that harnesses model consistency for robust LLM ensemble.<n> Token-level consistency captures fine-grained disagreements by applying a low-pass filter to downweight uncertain tokens.<n>Model-level consistency models global agreement by promoting model outputs with high self-confidence.
  arXiv  Detail & Related papers  (2025-10-12T04:18:45Z)
• Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection [7.183964892282175]
  This paper proposes a Generative Adversarial Network-based Synthetic Residential Load Pattern (RLP-GAN) generation model.<n>We develop a holistic evaluation method to validate the effectiveness of RLP-GAN using real-world data of 417 households.<n>We have publicly released the RLP-GAN generated synthetic dataset, which comprises one million synthetic residential load pattern profiles.
  arXiv  Detail & Related papers  (2025-04-19T13:50:49Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Improving $(α, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance [7.8973037023478785]
  Federated Learning (FL) is a potential solution to data privacy challenges in distributed machine learning.<n>FL systems remain vulnerable to Byzantine attacks, where malicious nodes contribute corrupted model updates.<n>This paper introduces Layerwise Cosine Aggregation, a novel aggregation scheme designed to enhance robustness of these rules in high-dimensional settings.
  arXiv  Detail & Related papers  (2025-03-27T08:07:39Z)
• Adaptive Multi-Fidelity Reinforcement Learning for Variance Reduction in Engineering Design Optimization [0.0]
  Multi-fidelity Reinforcement Learning (RL) frameworks efficiently utilize computational resources by integrating analysis models of varying accuracy and costs.<n>This work proposes a novel adaptive multi-fidelity RL framework, in which multiple heterogeneous, non-hierarchical low-fidelity models are dynamically leveraged alongside a high-fidelity model.<n>The effectiveness of the approach is demonstrated in an octocopter design optimization problem, utilizing two low-fidelity models alongside a high-fidelity simulator.
  arXiv  Detail & Related papers  (2025-03-23T22:29:08Z)
• Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging [36.00016254809852]
  This paper systematically compares the effectiveness of model merging and data mixture methods in constructing 3H-aligned LLMs.<n>We propose a novel textbfReweighting textbfEnhanced task textbfSingular textbfMerging method, textbfRESM, through outlier weighting and sparsity-aware rank selection strategies.
  arXiv  Detail & Related papers  (2025-02-08T11:56:58Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation [93.38604803625294]
  We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) We use Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-03T17:39:38Z)
• Progressively Label Enhancement for Large Language Model Alignment [42.01694160556464]
  Large Language Models (LLM) alignment aims to prevent models from producing content that misaligns with human expectations. We propose PLE, a framework that dynamically adjusts the model's training process based on the evolving quality of the generated data.
  arXiv  Detail & Related papers  (2024-08-05T16:21:17Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces [55.14361269378122]
  Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. We study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback-Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics.
  arXiv  Detail & Related papers  (2023-09-05T13:42:11Z)

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.