Enhancing Multilingual Reasoning via Steerable Model Merging

• URL: http://arxiv.org/abs/2606.19002v1
• Date: Wed, 17 Jun 2026 12:28:47 GMT
• Title: Enhancing Multilingual Reasoning via Steerable Model Merging
• Abstract summary: We propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model.<n>We show that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.
• Score: 53.27036725623993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reasoning tasks by aligning feature spaces of different models. However, the merged single model often fails to address the conflicts between source models, leading to suboptimal performance. In other words, the one-size-fits-all merging strategy may not align with the characteristics of different inputs which may require prioritizing certain models over others. To this end, we propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model. To realize this idea, we introduce a gated cross-attention mechanism to weight or filter the two attended source models in an adaptive manner. Extensive experiments demonstrate that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.

Related papers

• DiM\ extsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging [60.709970092170074]
  We propose Direction- and Magnitude-aware Multimodal merging (DiM3)<n>Experiments on multilingual benchmarks in both text-only and vision-language settings, covering 57 languages across LLaVA- and Qwen-based backbones.
  arXiv  Detail & Related papers  (2026-05-13T03:50:54Z)
• Unlocking the Power of Large Language Models for Multi-table Entity Matching [25.152180469437422]
  Multi-table entity matching (MEM) addresses the limitations of dual-table approaches.<n>We propose a novel framework for multi-table entity matching, termed LLM4MEM.<n>Our model improves by an average of 5.1% in F1 compared with the baseline model.
  arXiv  Detail & Related papers  (2026-04-23T03:13:44Z)
• Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation [49.98025799046136]
  We introduce Merge-And-GuidE, a two-stage framework that leverages model merging for guided decoding.<n>In Stage 1, MAGE resolves a compatibility problem between the guidance and base models.<n>In Stage 2, we merge explicit and implicit value models into a unified guidance proxy, which then steers the decoding of the base model from Stage 1.
  arXiv  Detail & Related papers  (2025-10-04T11:10:07Z)
• Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models [2.3193211674050516]
  This paper presents our approach to the multimodal track of the BabyLM challenge addressing this discrepancy.<n>We develop language-only and multimodal models in low-resource settings using developmentally plausible datasets.
  arXiv  Detail & Related papers  (2025-10-02T09:38:25Z)
• Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories [21.899117703417517]
  We propose a derivative-free optimization framework based on the evolutionary algorithm (Evo-Merging)<n>Our method consists of two key components: (1) sparsity-based denoising, designed to identify and filter out irrelevant or redundant information across models, and (2) sign-aware scaling, which dynamically computes optimal combination weights for the relevant models based on their performance.<n>Our approach achieves state-of-the-art results on a range of tasks, significantly outperforming existing strong baselines.
  arXiv  Detail & Related papers  (2025-09-16T10:55:50Z)
• Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units [29.79935180749153]
  This paper investigates the enhancement of reasoning capabilities in language models through token-level multi-model collaboration.<n>We introduce a distribution distance-based dynamic selection strategy (DDS) to optimize the multi-model collaboration process.
  arXiv  Detail & Related papers  (2025-08-26T07:41:33Z)
• 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)
• AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization [86.8133939108057]
  We propose AdaMMS, a novel model merging method tailored for heterogeneous MLLMs.<n>Our method tackles the challenges in three steps: mapping, merging and searching.<n>As the first model merging method capable of merging heterogeneous MLLMs without labeled data, AdaMMS outperforms previous model merging methods on various vision-language benchmarks.
  arXiv  Detail & Related papers  (2025-03-31T05:13:02Z)
• Exploring Model Kinship for Merging Large Language Models [73.98345036483299]
  We study model evolution through iterative merging, drawing an analogy to biological evolution.<n>We show that model kinship is closely linked to the performance improvements achieved by merging.<n>We propose a new model merging strategy: Top-k Greedy Merging with Model Kinship.
  arXiv  Detail & Related papers  (2024-10-16T14:29:29Z)
• Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging [11.186194228460273]
  We propose a preference-aware model merging problem in which the performance of the merged model on each base model's task is treated as an objective.<n>We show that the proposed model merging produces diverse trade-off models and achieves higher test accuracy compared to state-of-the-art merging baselines.
  arXiv  Detail & Related papers  (2024-08-22T03:41:14Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)

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.