ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline

ICLR 2026 Conference Submission16702 Authors

Keywords: Interactive Control Systems, Clarification-First Dialogue, Ambiguity Resolution, Hybrid Data Augmentation, Function-Calling Language Models, Human Validation and Robustness

Abstract:

Natural language interfaces for vehicle control must contend with vague commands, evolving dialogue context, and strict protocol constraints.
We introduce ClarifyVC, a unified framework that integrates a hybrid data-augmentation pipeline (ClarifyVC-Data), reference models trained on the data (ClarifyVC-Models)
and a evaluation protocol (ClarifyVC-Eval).
The agent-orchestrated pipeline generates diverse, ambiguity-rich dialogues from real-world seeded queries under schema and safety constraints, while the evaluation protocol systematically probes single-turn parsing, conservative clarification under extreme fuzziness, and multi-turn grounding.
Fine-tuning on ClarifyVC-Data yields consistent gains—up to 15\% higher parsing accuracy, 20\% stronger ambiguity resolution, and 98\% protocol compliance—across realistic in-cabin scenarios, with human-in-the-loop assessments confirming high realism, coherence, and applicability.
ClarifyVC thus advances beyond simulation-only datasets by tightly coupling real-world grounding with scalable generation and standardized evaluation, and provides a generalizable pipeline for broader interactive control domains.

Primary Area: datasets and benchmarks

Submission Number: 16702