Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zeyu, Li, Lei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.09343
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915998598168576
author Li, Zeyu
Li, Lei
author_facet Li, Zeyu
Li, Lei
contents Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, order metadata, historical interactions, and platform policies. Existing complaint understanding systems mainly perform shallow classification or template matching over isolated modalities, while underutilizing explicit scene structure, rule knowledge, and cross-evidence dependencies. To address this limitation, we present SKG-VLA for multimodal complaint decision making. The core idea is to model each case as a structured complaint scene and represent its decision-relevant semantics with a \emph{Scene Knowledge Graph} (SKG), which organizes complaint entities, evidence items, policy clauses, temporal events, transactional states, and action-relevant relations into a unified graph. Based on SKG, we build a data synthesis pipeline that generates complaint scene descriptions, rule-consistent graph generalizations, question-answer supervision, and decision recommendations. We further construct a large-scale complaint scene dataset with both text-only and multimodal in-domain benchmarks. Finally, we adopt a three-stage training strategy -- domain-adaptive pre-training, task-oriented instruction fine-tuning, and end-to-end multimodal alignment -- to inject structured scene priors into a multimodal decision model. Experiments show that SKG-VLA consistently improves policy-grounded reasoning, complaint decision accuracy, long-tail generalization, and robustness under incomplete evidence.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09343
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
Li, Zeyu
Li, Lei
Artificial Intelligence
Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, order metadata, historical interactions, and platform policies. Existing complaint understanding systems mainly perform shallow classification or template matching over isolated modalities, while underutilizing explicit scene structure, rule knowledge, and cross-evidence dependencies. To address this limitation, we present SKG-VLA for multimodal complaint decision making. The core idea is to model each case as a structured complaint scene and represent its decision-relevant semantics with a \emph{Scene Knowledge Graph} (SKG), which organizes complaint entities, evidence items, policy clauses, temporal events, transactional states, and action-relevant relations into a unified graph. Based on SKG, we build a data synthesis pipeline that generates complaint scene descriptions, rule-consistent graph generalizations, question-answer supervision, and decision recommendations. We further construct a large-scale complaint scene dataset with both text-only and multimodal in-domain benchmarks. Finally, we adopt a three-stage training strategy -- domain-adaptive pre-training, task-oriented instruction fine-tuning, and end-to-end multimodal alignment -- to inject structured scene priors into a multimodal decision model. Experiments show that SKG-VLA consistently improves policy-grounded reasoning, complaint decision accuracy, long-tail generalization, and robustness under incomplete evidence.
title SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
topic Artificial Intelligence
url https://arxiv.org/abs/2605.09343