Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance

• URL: http://arxiv.org/abs/2603.27536v1
• Date: Sun, 29 Mar 2026 06:20:08 GMT
• Title: Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance
• Abstract summary: This paper presents a scenario-centric framework for reproducible auditing of risk reasoning in urban driving contexts.<n>Findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.
• Score: 3.7098231493739764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced Driver Assistance Systems (ADAS) increasingly rely on learning-based perception, yet safety-relevant failures often arise without component malfunction, driven instead by partial observability and semantic ambiguity in how risk is interpreted and communicated. This paper presents a scenario-centric framework for reproducible auditing of LLM-based risk reasoning in urban driving contexts. Deterministic, temporally bounded scenario windows are constructed from multimodal driving data and evaluated under fixed prompt constraints and a closed numeric risk schema, ensuring structured and comparable outputs across models. Experiments on a curated near-people scenario set compare two text-only models and one multimodal model under identical inputs and prompts. Results reveal systematic inter-model divergence in severity assignment, high-risk escalation, evidence use, and causal attribution. Disagreement extends to the interpretation of vulnerable road user presence, indicating that variability often reflects intrinsic semantic indeterminacy rather than isolated model failure. These findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.

Related papers

• Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning [65.15766304205657]
  In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile.<n>Our analysis reveals that the fundamental limitation lies in an inductive gap, models often produce correct answers from flawed reasoning.<n>We introduce a framework that restructures multimodal ICL as a principled inductive-deductive process.
  arXiv  Detail & Related papers  (2026-05-04T09:18:19Z)
• SG-CADVLM: A Context-Aware Decoding Powered Vision Language Model for Safety-Critical Scenario Generation [8.490714399662453]
  This paper presents SG-CADVLM, a framework that integrates Context-Aware Decoding with multi-modal input processing to generate safety-critical scenarios.<n>The framework mitigates VLM hallucination issues while enabling the simultaneous generation of road geometry and vehicle trajectories.
  arXiv  Detail & Related papers  (2026-01-26T12:53:12Z)
• Semantic Misalignment in Vision-Language Models under Perceptual Degradation [2.9140696506330723]
  We study semantic misalignment in Vision-Language Models (VLMs) under controlled degradation of visual perception.<n>We observe severe failures in downstream VLM behavior, including hallucinated object mentions, omission of safety-critical entities, and inconsistent safety judgments.<n>Our results reveal a clear disconnect between pixel-level robustness and multimodal semantic reliability, highlighting a critical limitation of current VLM-based systems.
  arXiv  Detail & Related papers  (2026-01-13T09:13:05Z)
• Unsupervised Learning for Detection of Rare Driving Scenarios [1.5399429731150376]
  This research explores an unsupervised learning framework for detecting rare and extreme driving scenarios.<n>We leverage the recently proposed Deep Isolation Forest (DIF) to identify non-linear and complex anomalies.<n>Our results demonstrate that the proposed approach effectively identifies rare and hazardous driving scenarios.
  arXiv  Detail & Related papers  (2025-12-29T16:35:20Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
  We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
  arXiv  Detail & Related papers  (2025-09-24T13:35:15Z)
• When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models [50.66979825532277]
  We introduce Safe-Semantics-but-Unsafe-Interpretation (SSUI), the first dataset featuring interpretable reasoning paths tailored for a cross-modal challenge.<n>A novel training framework, Safety-aware Reasoning Path Optimization (SRPO), is also designed based on the SSUI dataset.<n> Experimental results show that our SRPO-trained models achieve state-of-the-art results on key safety benchmarks.
  arXiv  Detail & Related papers  (2025-09-15T15:40:58Z)
• Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios [1.5367554212163714]
  This paper presents a Case-Based Reasoning Augmented Large Language Model (CBR-LLM) framework for evasive maneuver decision-making in complex risk scenarios.<n>Our approach integrates semantic scene understanding from dashcam video inputs with the retrieval of relevant past driving cases.<n>Experiments show that our framework improves decision accuracy, justification quality, and alignment with human expert behavior.
  arXiv  Detail & Related papers  (2025-06-25T15:19:25Z)
• From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios [6.681744368557208]
  Large Language Models (LLMs) and structured scenario parsing and prompt engineering are used to generate safety-critical driving scenarios.<n>We validate our approach using a 2D simulation framework and multiple pre-trained LLMs.<n>We conclude that an LLM equipped with domain-informed prompting techniques can effectively evaluate and generate safety-critical driving scenarios.
  arXiv  Detail & Related papers  (2025-02-04T09:19:13Z)
• Generating Out-Of-Distribution Scenarios Using Language Models [58.47597351184034]
  Large Language Models (LLMs) have shown promise in autonomous driving. This paper introduces a framework for generating diverse Out-Of-Distribution (OOD) driving scenarios. We evaluate our framework through extensive simulations and introduce a new "OOD-ness" metric.
  arXiv  Detail & Related papers  (2024-11-25T16:38:17Z)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective [82.90376711290808]
  This paper explores the integration of Large Language Models (LLMs) into Autonomous Driving systems. LLMs are intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine.
  arXiv  Detail & Related papers  (2023-11-28T03:13:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.