It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization

• URL: http://arxiv.org/abs/2407.00487v3
• Date: Sun, 24 Nov 2024 14:11:56 GMT
• Title: It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization
• Authors: Bingdong Li, Zixiang Di, Yanting Yang, Hong Qian, Peng Yang, Hao Hao, Ke Tang, Aimin Zhou,
• Abstract summary: The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that outperforms any of the individual source models. Existing methods rely heavily on human knowledge or intuition. It's difficult to obtain the great model merging configuration in limited evaluations.
• Score: 16.54335356612006
• License:
• Abstract: In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that outperforms any of the individual source models. However, model merging faces two significant challenges: First, existing methods rely heavily on human knowledge or intuition. Second, it's difficult to obtain the great model merging configuration in limited evaluations. To address these challenges, we formalize model merging as a multi-objective optimization problem and propose an automated optimization approach named MM-MO. This method leverages multi-objective optimization algorithms to autonomously search for optimal merging configurations across various tasks, alleviating the need for human intervention. In MM-MO, a weak-to-strong method is employed to enhance the acquisition function, allowing previously evaluated superior configurations to guide the search for new ones. Meanwhile, Fisher information is applied to screen these configurations, increasing the possibility of identifying high-quality merging configuration. Additionally, we designed a sparsity metric as an additional optimization objective to enhance the model's generalization performance across different tasks. We conducted comprehensive experiments with other mainstream model merging methods, demonstrating that the proposed MM-MO algorithm is competitive and effective in achieving high-quality model merging.

Related papers

• Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging [30.38047100067552]
  Reasoning capabilities represent a critical frontier for large language models. One way to efficiently supplement capabilities with is by model merging. We propose an Automated Model Merging Framework that enables fine-grained exploration of merging strategies.
  arXiv  Detail & Related papers  (2025-02-06T12:47:25Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [74.02034188307857]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. We find existing methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance. Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
  arXiv  Detail & Related papers  (2025-01-02T12:45:21Z)
• Surrogate-assisted multi-objective design of complex multibody systems [1.1650821883155187]
  We present a back-and-forth approach between surrogate modeling and multi-objective optimization. We compare different strategies regarding multi-objective optimization, sampling and also surrogate modeling.
  arXiv  Detail & Related papers  (2024-12-19T13:48:49Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization process to enhance the multimodal reasoning capabilities of MLLMs. We develop a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models [28.993221775758702]
  Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. This paper marks a significant advance toward more flexible and comprehensive model merging techniques. We train policy and value networks using offline sampling of weight vectors, which are then employed for the online optimization of merging strategies.
  arXiv  Detail & Related papers  (2024-09-27T16:31:31Z)
• Decoding-Time Language Model Alignment with Multiple Objectives [116.42095026960598]
  Existing methods primarily focus on optimizing LMs for a single reward function, limiting their adaptability to varied objectives. Here, we propose $textbfmulti-objective decoding (MOD)$, a decoding-time algorithm that outputs the next token from a linear combination of predictions. We show why existing approaches can be sub-optimal even in natural settings and obtain optimality guarantees for our method.
  arXiv  Detail & Related papers  (2024-06-27T02:46:30Z)
• Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [53.33473557562837]
  Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost. We propose a practical and scalable approach to solve this problem via mixture of experts (MoE) based model fusion. By ensembling the weights of specialized single-task models, the MoE module can effectively capture the trade-offs between multiple objectives.
  arXiv  Detail & Related papers  (2024-06-14T07:16:18Z)
• Pareto Set Learning for Neural Multi-objective Combinatorial Optimization [6.091096843566857]
  Multiobjective optimization (MOCO) problems can be found in many real-world applications. We develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure. Our proposed method significantly outperforms some other methods on the multiobjective traveling salesman problem, multiconditioned vehicle routing problem and multi knapsack problem in terms of solution quality, speed, and model efficiency.
  arXiv  Detail & Related papers  (2022-03-29T09:26:22Z)
• Leveraging Trust for Joint Multi-Objective and Multi-Fidelity Optimization [0.0]
  This paper investigates a novel approach to Bayesian multi-objective and multi-fidelity (MOMF) optimization. We suggest the innovative use of a trust metric to support simultaneous optimization of multiple objectives and data sources. Our methods offer broad applicability in solving simulation problems in fields such as plasma physics and fluid dynamics.
  arXiv  Detail & Related papers  (2021-12-27T20:55:26Z)
• A survey on multi-objective hyperparameter optimization algorithms for Machine Learning [62.997667081978825]
  This article presents a systematic survey of the literature published between 2014 and 2020 on multi-objective HPO algorithms. We distinguish between metaheuristic-based algorithms, metamodel-based algorithms, and approaches using a mixture of both. We also discuss the quality metrics used to compare multi-objective HPO procedures and present future research directions.
  arXiv  Detail & Related papers  (2021-11-23T10:22:30Z)

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.