Talk, Snap, Complain: Validation-Aware Multimodal Expert Framework for Fine-Grained Customer Grievances

TL;DR

This paper introduces VALOR, a multimodal, validation-aware framework that improves fine-grained customer complaint classification by integrating textual and visual data with expert reasoning, enhancing robustness and contextual understanding.

Contribution

The paper presents VALOR, a novel multimodal, validation-aware learning framework with expert routing and semantic alignment, advancing complaint analysis beyond unimodal approaches.

Findings

VALOR outperforms baseline models on a curated complaint dataset.

It effectively handles complex scenarios with distributed multimodal information.

The framework supports sustainable development goals related to industry and responsible consumption.

Abstract

Existing approaches to complaint analysis largely rely on unimodal, short-form content such as tweets or product reviews. This work advances the field by leveraging multimodal, multi-turn customer support dialogues, where users often share both textual complaints and visual evidence (e.g., screenshots, product photos) to enable fine-grained classification of complaint aspects and severity. We introduce VALOR, a Validation-Aware Learner with Expert Routing, tailored for this multimodal setting. It employs a multi-expert reasoning setup using large-scale generative models with Chain-of-Thought (CoT) prompting for nuanced decision-making. To ensure coherence between modalities, a semantic alignment score is computed and integrated into the final classification through a meta-fusion strategy. In alignment with the United Nations Sustainable Development Goals (UN SDGs), the proposed framework supports SDG 9 (Industry, Innovation and Infrastructure) by advancing AI-driven tools for robust, scalable, and context-aware service infrastructure. Further, by enabling structured analysis of complaint narratives and visual context, it contributes to SDG 12 (Responsible Consumption and Production) by promoting more responsive product design and improved accountability in consumer services. We evaluate VALOR on a curated multimodal complaint dataset annotated with fine-grained aspect and severity labels, showing that it consistently outperforms baseline models, especially in complex complaint scenarios where information is distributed across text and images. This study underscores the value of multimodal interaction and expert validation in practical complaint understanding systems. Resources related to data and codes are available here: https://github.com/sarmistha-D/VALOR