Search papers, labs, and topics across Lattice.
The paper introduces RideJudge, a Progressive Visual-Logic-Aligned Framework, to automate and improve the adjudication of responsibility disputes in ride-hailing services. RideJudge uses a synthesis engine (SynTraj) to ground abstract liability concepts into concrete trajectory patterns, an adaptive context optimization strategy to distill expert knowledge, and a chain-of-adjudication mechanism for evidentiary inquiry. Ordinal-Sensitive Reinforcement Learning is used to calibrate decision boundaries against hierarchical severity, achieving 88.41% accuracy with an 8B parameter model, outperforming 32B baselines.
An 8B parameter model, RideJudge, outperforms 32B baselines in ride-hailing dispute adjudication by aligning visual semantics with evidentiary protocols, achieving 88.41% accuracy.
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.
