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

arXiv: https://arxiv.org/abs/2609.10177 · HTML: https://mlsanity.com/paper/2609.10177/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 70 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 18 of 18)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [In-context Learning with Retrieved Demonstrations for Language Models: A Survey](https://mlsanity.com/paper/2401.11624/) (2024)
- [Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS](https://mlsanity.com/paper/2411.18478/) (2024)
- [ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification](https://mlsanity.com/paper/2502.14565/) (2025)
- [M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering](https://mlsanity.com/paper/2504.04633/) (2025)
- [Supervised Knowledge Makes Large Language Models Better In-context Learners](https://mlsanity.com/paper/2312.15918/) (2023)
- [Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation](https://mlsanity.com/paper/2603.04466/) (2026)
- [Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning](https://mlsanity.com/paper/2404.07546/) (2024)
- [Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models](https://mlsanity.com/paper/2506.07936/) (2025)
- [Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning](https://mlsanity.com/paper/2602.09850/) (2026)
- [Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers](https://mlsanity.com/paper/2601.20796/) (2026)
- [ICLR: In-Context Imitation Learning with Visual Reasoning](https://mlsanity.com/paper/2603.07530/) (2026)
- [Enhancing Visual In-Context Learning by Multi-Faceted Fusion](https://mlsanity.com/paper/2601.10107/) (2026)
- [Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization](https://mlsanity.com/paper/2606.31373/) (2026)

## Built on by (most cited first, 1 of 1)

- [SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation](https://mlsanity.com/paper/2609.16601/) (2026)

## Abstract (arXiv)

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).