LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations

TL;DR

LIMSSR introduces a novel LLM-driven framework for sequence-to-score reasoning in multimodal learning with incomplete training data, avoiding reliance on full-modal observations and improving data efficiency.

Contribution

It reformulates incomplete multimodal learning as a sequence reasoning task and employs prompt-guided imputation and fusion to handle missing data without hallucinations.

Findings

Outperforms state-of-the-art methods on three datasets.

Effectively handles training-time incomplete observations.

Establishes a new paradigm for data-efficient multimodal learning.

Abstract

Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availability during training to provide reconstruction supervision or cross-modal priors. This paper tackles the more challenging setting of IML under training-time incomplete observations, which precludes reliance on a ``God's eye view'' of complete data. We propose LIMSSR (LLM-Driven Incomplete Multimodal Sequence-to-Score Reasoning), a framework that reformulates this challenge as a conditional sequence reasoning task. LIMSSR leverages the semantic reasoning capabilities of Large Language Models via Prompt-Guided Context-Aware Modality Imputation and Multidimensional Representation Fusion to infer latent semantics from available contexts without direct reconstruction. To mitigate hallucinations, we introduce a Mask-Aware Dual-Path Aggregation to dynamically calibrate inference uncertainty. Extensive experiments on three Action Quality Assessment datasets demonstrate that LIMSSR significantly outperforms state-of-the-art baselines without relying on complete training data, establishing a new paradigm for data-efficient multimodal learning. Code is available at https://github.com/XuHuangbiao/LIMSSR.