SymDPO：基于符号演示直接偏好优化增强大型多模态模型的上下文学习能力

摘要

随着语言模型规模的持续扩大，大型语言模型（LLMs）在上下文学习（ICL）中展现出新兴能力，能够通过前置少量上下文示例（ICDs）作为语境来解决语言任务。受这些进展启发，研究者将此类技术拓展至多模态领域，开发出具备上下文学习能力的大型多模态模型（LMMs）。然而，现有LMMs面临一个关键问题：它们往往难以有效利用多模态示例中的视觉上下文，而只是简单地遵循文本模式。这表明LMMs尚未实现多模态示例与模型输出之间的有效对齐。为解决这一问题，我们提出符号演示直接偏好优化（SymDPO）。具体而言，SymDPO通过用随机符号替换示例中的文本答案，旨在打破构建多模态示例的传统范式。这种方法迫使模型深入理解演示图像，并建立图像与符号之间的关联以正确回答问题。我们在多个基准测试上验证了该方法的有效性，结果表明采用SymDPO的LMMs能更有效地理解示例中的多模态上下文，并利用这些知识更好地回答问题。

English

As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, existing LMMs face a critical issue: they often fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. This indicates that LMMs do not achieve effective alignment between multimodal demonstrations and model outputs. To address this problem, we propose Symbol Demonstration Direct Preference Optimization (SymDPO). Specifically, SymDPO aims to break the traditional paradigm of constructing multimodal demonstrations by using random symbols to replace text answers within instances. This forces the model to carefully understand the demonstration images and establish a relationship between the images and the symbols to answer questions correctly. We validate the effectiveness of this method on multiple benchmarks, demonstrating that with SymDPO, LMMs can more effectively understand the multimodal context within examples and utilize this knowledge to answer questions better.

SymDPO：基于符号演示直接偏好优化增强大型多模态模型的上下文学习能力

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

摘要

Support