A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication

2026-03-17

AI Summary

This work proposes RideJudge, a novel framework addressing key challenges in automated adjudication of ride-hailing liability disputes—namely, the misalignment between visual semantics and evidential logic, opaque reasoning processes, and the tension between extensive legal regulations and model context limitations. RideJudge introduces a progressive adjudication mechanism that aligns visual and logical reasoning through SynTraj, a synthetic trajectory engine that concretizes abstract liability concepts. It integrates adaptive context optimization and a Chain-of-Adjudication to enable interpretable decision-making, while ordinal-sensitive reinforcement learning precisely calibrates liability severity boundaries. Built upon a multimodal large language model, RideJudge-8B achieves 88.41% accuracy on liability determination tasks, outperforming 32B-scale baselines and establishing a new paradigm for high-accuracy, explainable judicial decision support.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. Although Multimodal LLMs offer a promising paradigm, they fundamentally struggle to bridge the gap between general visual semantics and rigorous evidentiary protocols, often leading to perceptual hallucinations and logical looseness. To address these systemic misalignments, we introduce RideJudge, a Progressive Visual-Logic-Aligned Framework. Instead of relying on generic pre-training, we bridge the semantic gap via SynTraj, a synthesis engine that grounds abstract liability concepts into concrete trajectory patterns. To resolve the conflict between massive regulation volume and limited context windows, we propose an Adaptive Context Optimization strategy that distills expert knowledge, coupled with a Chain-of-Adjudication mechanism to enforce active evidentiary inquiry. Furthermore, addressing the inadequacy of sparse binary feedback for complex liability assessment, we implement a novel Ordinal-Sensitive Reinforcement Learning mechanism that calibrates decision boundaries against hierarchical severity. Extensive experiments show that our RideJudge-8B achieves 88.41\% accuracy, surpassing 32B-scale baselines and establishing a new standard for interpretable adjudication.

Problem

• ride-hailing adjudication
• responsibility dispute
• multimodal reasoning
• evidentiary protocol
• interpretable AI

Innovation

• Visual-Logic Alignment
• SynTraj
• Chain-of-Adjudication
• Ordinal-Sensitive Reinforcement Learning
• Adaptive Context Optimization