Multi-task Code LLMs: Data Mix or Model Merge?

• URL: http://arxiv.org/abs/2601.21115v1
• Date: Wed, 28 Jan 2026 23:06:09 GMT
• Title: Multi-task Code LLMs: Data Mix or Model Merge?
• Authors: Mingzhi Zhu, Boris Sobolev, Rahul Krishna, Raju Pavuluri, Stacy Patterson, Michele Merler,
• Abstract summary: We compare two approaches for creating small, multi-task code LLMs: data mixing versus model merging.<n>Our evaluation on HumanEval, MBPP, and CodeXGlue benchmarks reveals that model merging achieves the best overall performance at larger scale.
• Score: 5.741318641887549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learning that balance performance, constraints, and costs. We compare two approaches for creating small, multi-task code LLMs: data mixing versus model merging. We conduct extensive experiments across two model families (Qwen Coder and DeepSeek Coder) at two scales (2B and 7B parameters), fine-tuning them for code generation and code summarization tasks. Our evaluation on HumanEval, MBPP, and CodeXGlue benchmarks reveals that model merging achieves the best overall performance at larger scale across model families, retaining 96% of specialized model performance on code generation tasks while maintaining summarization capabilities. Notably, merged models can even surpass individually fine-tuned models, with our best configuration of Qwen Coder 2.5 7B model achieving 92.7% Pass@1 on HumanEval compared to 90.9% for its task-specific fine-tuned equivalent. At a smaller scale we find instead data mixing to be a preferred strategy. We further introduce a weight analysis technique to understand how different tasks affect model parameters and their implications for merging strategies. The results suggest that careful merging and mixing strategies can effectively combine task-specific capabilities without significant performance degradation, making them ideal for resource-constrained deployment scenarios.

Related papers

• 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)
• MergeBench: A Benchmark for Merging Domain-Specialized LLMs [25.333088749417414]
  MergeBench is an evaluation suite designed to assess model merging at scale.<n>It builds on state-of-the-art open-source language models, including Llama and Gemma families at 2B to 9B scales.<n>We assess eight representative merging methods across multi-task performance, forgetting and runtime efficiency.
  arXiv  Detail & Related papers  (2025-05-16T04:02:55Z)
• Dynamic Fisher-weighted Model Merging via Bayesian Optimization [37.02810891820468]
  Existing merging approaches typically involve scaling the parameters model-wise or integrating parameter importance parameter-wise.<n>We unify these strategies into a more general merging framework, and introduce Dynamic Fisher-weighted Merging (DF-Merge)<n>We show that DF-Merge outperforms strong baselines across models of different sizes and a variety of tasks.
  arXiv  Detail & Related papers  (2025-04-26T18:31:14Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach [0.0]
  LEWIS (Layer Wise Sparsity) is a guided model-merging framework.<n>It guides existing merging methods by preserving essential layer-wise task-specific knowledge.<n>Experiments demonstrate the effectiveness of LEWIS with performance improvements of code instruction-following and math-solving models.
  arXiv  Detail & Related papers  (2025-03-05T20:09:59Z)
• 1bit-Merging: Dynamic Quantized Merging for Large Language Models [19.365673988498028]
  We present texttt1bit-Merging, a novel framework that integrates task-specific routing with 1-bit quantized task vectors to balance performance and storage efficiency.<n>We demonstrate that 1bit-Merging achieves comparable or superior performance to existing methods while significantly reducing storage requirements.
  arXiv  Detail & Related papers  (2025-02-15T09:47:50Z)
• 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.<n>One way to efficiently supplement capabilities with is by model merging.<n>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 [72.10987117380584]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods discard task-specific information that, while causing conflicts, is crucial for performance.<n>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)
• 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)
• Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion [86.6191592951269]
  Merging models fine-tuned from common extensively pretrained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multitask model that performs well across diverse tasks. We propose the CONtinuous relaxation dis (Concrete) subspace learning method to identify a common lowdimensional subspace and utilize its shared information track interference problem without sacrificing performance.
  arXiv  Detail & Related papers  (2023-12-11T07:24:54Z)
• An Empirical Study of Multimodal Model Merging [148.48412442848795]
  Model merging is a technique that fuses multiple models trained on different tasks to generate a multi-task solution. We conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture. We propose two metrics that assess the distance between weights to be merged and can serve as an indicator of the merging outcomes.
  arXiv  Detail & Related papers  (2023-04-28T15:43:21Z)

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.