Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning

• URL: http://arxiv.org/abs/2609.10177v1
• Date: Wed, 09 Sep 2026 13:45:02 GMT
• Title: Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning
• Abstract summary: In-context learning (ICL) is widely used in multimodal large language models (MLLMs)<n>Existing ICL methods often rely on surface level imitation of in-context demonstrations.<n>We propose a new multimodal ICL framework that combines contrastive demonstration modeling with the self-refinement capability of MLLMs.
• Score: 8.500110048966242
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-context learning (ICL) is widely used in multimodal large language models (MLLMs) and achieves strong performance across a wide range of multimodal tasks. However, existing multimodal ICL methods often rely on surface level imitation of in-context demonstrations, making it difficult for MLLMs to align their responses with the reasoning path required by the given multimodal input. This limitation becomes more pronounced in complex multimodal tasks, thereby restricting further improvements in MLLM performance. To address this issue, we propose a new multimodal ICL framework that combines contrastive demonstration modeling with the self-refinement capability of MLLMs. Specifically, our framework reformulates each demonstration by explicitly contrasting a suboptimal response with a better response under the same input, together with a reasoning path that reveals how the response should be refined. This contrastive formulation makes the reasoning path toward the desired response more explicit and guides the MLLM beyond superficial imitation. Furthermore, because effective refinement depends on the current response, we introduce a response-conditioned retrieval mechanism to select demonstrations whose reasoning paths are more relevant to the current response. In addition, we use a lightweight alignment controller to predict response quality and determine whether further refinement is needed. Experiments on three types of multimodal tasks show that the proposed framework consistently improves MLLM performance, with particularly notable gains on visual question answering (VQA).

Related papers

• MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs [0.0]
  We propose a Multimodal Adaptive Few-Shot Prompting (MAF) framework for sentiment analysis.<n>MAF retrieves and integrates query-relevant demonstrations to elicit the sentiment reasoning capabilities of MLLMs in a context-sensitive manner.<n>Experiments on public benchmark datasets demonstrate that MAF achieves substantial and consistent performance improvements.
  arXiv  Detail & Related papers  (2026-06-14T09:16:36Z)
• Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis [5.3558051475405515]
  We introduce Multi-View Prompting (LLM-MvP), which adapts the multi-view principle of considering multiple element orderings to LLM prompting.<n>LLM-MvP achieves performance competitive or superior to finetuned approaches while substantially reducing computational overhead.
  arXiv  Detail & Related papers  (2026-05-27T07:04:39Z)
• Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition [51.68340973140949]
  Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions.<n> MLLMs exhibit $textbfmodality bias$, including visual bias and textual bias, which stems from their tendency to take unimodal shortcuts.<n>We propose Modality-aware Consistency Reasoning ($bfMCR$), which enforces structured cross-modal reasoning.
  arXiv  Detail & Related papers  (2026-02-04T12:12:49Z)
• Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval [25.629529312687694]
  We propose Reasoning Guided Embeddings (RGE), which preserves the generative rationale process of Multimodal Large Language Models (MLLMs)<n>Our method first enables the model to perform structured rationale generation conditioned on the instruction, and then extracts representations after reasoning has unfolded.<n>Experiments on the MMEB benchmark show that reasoning-guided conditioning improves multimodal retrieval performance by 4.9% over the non-reasoning baseline.
  arXiv  Detail & Related papers  (2025-11-20T08:44:47Z)
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models [85.30893355216486]
  We study how visual token redundancy evolves with different dMLLM architectures and tasks.<n>Our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks.<n>Layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs.
  arXiv  Detail & Related papers  (2025-11-19T04:13:36Z)
• EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models [64.70546873396624]
  We present the Extremely Complex Instruction Following Benchmark (EIFBENCH) for evaluating large language models (LLMs)<n>EIFBENCH includes multi-task scenarios that enable comprehensive assessment across diverse task types concurrently.<n>We also propose the Segment Policy Optimization (SegPO) algorithm to enhance the LLM's ability to accurately fulfill multi-task workflow.
  arXiv  Detail & Related papers  (2025-06-10T02:39:55Z)
• Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward [77.34936657745578]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)
• 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)
• Evaluating and Steering Modality Preferences in Multimodal Large Language Model [42.828461839307174]
  Multimodal large language models (MLLMs) have achieved remarkable performance on complex tasks with multimodal context.<n>We show that all 18 tested MLLMs generally demonstrate clear modality bias, and modality preference can be influenced by external interventions.<n>We propose a probing and steering method based on representation engineering to explicitly control modality preference.
  arXiv  Detail & Related papers  (2025-05-27T10:07:59Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• Model Composition for Multimodal Large Language Models [71.5729418523411]
  We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model. Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
  arXiv  Detail & Related papers  (2024-02-20T06:38:10Z)
• On the Performance of Multimodal Language Models [4.677125897916577]
  This study conducts a comparative analysis of different multimodal instruction tuning approaches. We reveal key insights for guiding architectural choices when incorporating multimodal capabilities into large language models.
  arXiv  Detail & Related papers  (2023-10-04T23:33:36Z)

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.