X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles

TL;DR

This paper introduces X-Blocks, a hierarchical framework analyzing linguistic components of natural language explanations for automated vehicles, improving understanding of how explanations are constructed across different driving scenarios.

Contribution

The paper presents a novel hierarchical analytical framework, X-Blocks, including RACE for classifying explanations, revealing linguistic patterns at context, syntax, and lexicon levels.

Findings

RACE achieves 91.45% accuracy in classifying explanations

Explanations use a limited set of reusable grammatical structures

Vocabulary patterns are context-specific and distinguish driving scenarios

Abstract

Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales across diverse scenarios. This paper introduces X-Blocks (eXplanation Blocks), a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon. At the context level, we propose RACE (Reasoning-Aligned Classification of Explanations), a multi-LLM ensemble framework that combines Chain-of-Thought reasoning with self-consistency mechanisms to robustly classify explanations into 32 scenario-aware categories. Applied to human-authored explanations from the Berkeley DeepDrive-X dataset, RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification. At the lexical level, log-odds analysis with informative Dirichlet priors reveals context-specific vocabulary patterns that distinguish driving scenarios. At the syntactic level, dependency parsing and template extraction show that explanations draw from a limited repertoire of reusable grammar families, with systematic variation in predicate types and causal constructions across contexts. The X-Blocks framework is dataset-agnostic and task-independent, offering broad applicability to other automated driving datasets and safety-critical domains. Overall, our findings provide evidence-based linguistic design principles for generating scenario-aware explanations that support transparency, user trust, and cognitive accessibility in automated driving systems.