Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?

• URL: http://arxiv.org/abs/2510.14387v1
• Date: Thu, 16 Oct 2025 07:38:16 GMT
• Title: Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
• Abstract summary: Math reasoning has been one crucial ability of large language models (LLMs)<n>We propose IP-Merging that first identifies the reasoning-associated parameters in both MLLM and Math LLM, then projects them into the subspace of MLLM.<n>IP-Merging is a tuning-free approach since parameters are directly adjusted.
• Score: 45.99128235364487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Math reasoning has been one crucial ability of large language models (LLMs), where significant advancements have been achieved in recent years. However, most efforts focus on LLMs by curating high-quality annotation data and intricate training (or inference) paradigms, while the math reasoning performance of multi-modal LLMs (MLLMs) remains lagging behind. Since the MLLM typically consists of an LLM and a vision block, we wonder: Can MLLMs directly absorb math reasoning abilities from off-the-shelf math LLMs without tuning? Recent model-merging approaches may offer insights into this question. However, they overlook the alignment between the MLLM and LLM, where we find that there is a large gap between their parameter spaces, resulting in lower performance. Our empirical evidence reveals two key factors behind this issue: the identification of crucial reasoning-associated layers in the model and the mitigation of the gaps in parameter space. Based on the empirical insights, we propose IP-Merging that first identifies the reasoning-associated parameters in both MLLM and Math LLM, then projects them into the subspace of MLLM, aiming to maintain the alignment, and finally merges parameters in this subspace. IP-Merging is a tuning-free approach since parameters are directly adjusted. Extensive experiments demonstrate that our IP-Merging method can enhance the math reasoning ability of MLLMs directly from Math LLMs without compromising their other capabilities.

Related papers

• RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval [2.2125276321198677]
  Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates.<n>Recent breakthroughs in multimodal large language models (MLLMs) boost MMIR performance by incorporating MLLM knowledge under the contrastive finetuning framework.<n>We introduce a novel framework, RetLLM, designed to query MLLMs for MMIR in a training- and data-free manner.
  arXiv  Detail & Related papers  (2026-02-25T10:31:32Z)
• LLM4VV: Evaluating Cutting-Edge LLMs for Generation and Evaluation of Directive-Based Parallel Programming Model Compiler Tests [7.6818904666624395]
  This paper proposes a dual-LLM system and experiments with the usage of LLMs for the generation of compiler tests.<n>It is evident that LLMs possess the promising potential to generate quality compiler tests and verify them automatically.
  arXiv  Detail & Related papers  (2025-07-29T02:34:28Z)
• Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning [95.44766931218896]
  Multi-modal large language models (MLLMs) still lag behind text-based reasoning.<n>We introduce Perception-Reasoning Decoupling, which modularizes the MLLM's reasoning component and makes it easily replaceable.<n>We propose a novel reinforcement learning algorithm called Visual Perception Optimization (VPO) to align the MLLM's perceptual output with the final reasoning task.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning [3.0449420665138485]
  Large Language Models (LLMs) have raised interest in their formal reasoning capabilities, particularly in mathematics.<n>We propose a post-training approach leveraging a mixture of opinions (MoO) from weaker ancillary LLMs to enhance a (relatively) stronger LLM's reasoning.<n>Our results show that incorporating weaker LLMs' opinions improves mathematical reasoning by an average of 5%, highlighting the value of diverse perspectives in reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-26T23:22:02Z)
• Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement [72.97553348776425]
  We make a pioneering effort to broaden the applicability of merging techniques from FT to PT LLMs. We introduce an approach based on WeIght DisENtanglement (WIDEN) to effectively extend the merging scope. We merge Qwen1.5-Chat (an FT LLM with instruction-following skills) with Sailor (a PT LLM with multilingual abilities) across 7B and 14B model scales.
  arXiv  Detail & Related papers  (2024-08-06T10:46:46Z)
• Intermittent Semi-working Mask: A New Masking Paradigm for LLMs [13.271151693864114]
  Multi-turn dialogues are a key interaction method between humans and Large Language Models (LLMs) We propose a novel masking scheme called Intermittent Semi-working Mask (ISM) to address these problems.
  arXiv  Detail & Related papers  (2024-08-01T13:22:01Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks [18.068035947969044]
  There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. We argue that auto-regressive LLMs cannot, by themselves, do planning or self-verification. We present a vision of bf LLM-Modulo Frameworks that combine the strengths of LLMs with external model-based verifiers.
  arXiv  Detail & Related papers  (2024-02-02T14:43:18Z)
• Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity [61.54815512469125]
  This survey addresses the crucial issue of factuality in Large Language Models (LLMs) As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
  arXiv  Detail & Related papers  (2023-10-11T14:18:03Z)

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.