Chain of Questions: Guiding Multimodal Curiosity in Language Models
This addresses the challenge of proactive modality engagement in complex real-world environments for multimodal AI systems, representing an incremental advancement.
The paper tackles the problem of improving reasoning in multimodal language models by introducing the Chain of Questions (CoQ) framework, which dynamically generates questions to guide modality selection, resulting in improved accuracy, interpretability, and alignment on a novel benchmark dataset.
Reasoning capabilities in large language models (LLMs) have substantially advanced through methods such as chain-of-thought and explicit step-by-step explanations. However, these improvements have not yet fully transitioned to multimodal contexts, where models must proactively decide which sensory modalities such as vision, audio, or spatial perception to engage when interacting with complex real-world environments. In this paper, we introduce the Chain of Questions (CoQ) framework, a curiosity-driven reasoning approach that encourages multimodal language models to dynamically generate targeted questions regarding their surroundings. These generated questions guide the model to selectively activate relevant modalities, thereby gathering critical information necessary for accurate reasoning and response generation. We evaluate our framework on a novel multimodal benchmark dataset, assembled by integrating WebGPT, ScienceQA, AVSD, and ScanQA datasets. Experimental results demonstrate that our CoQ method improves a foundation model's ability to effectively identify and integrate pertinent sensory information. This leads to improved accuracy, interpretability, and alignment of the reasoning process with diverse multimodal tasks.