A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911593664610304 |
|---|---|
| author | Reis, Philipp Rigoll, Philipp Zehetner, Martin Henle, Jacqueline Otten, Stefan Sax, Eric |
| author_facet | Reis, Philipp Rigoll, Philipp Zehetner, Martin Henle, Jacqueline Otten, Stefan Sax, Eric |
| contents | Data-driven systems depend on task-relevant data, yet data collection pipelines remain passive and indiscriminate. Continuous logging of multimodal sensor streams incurs high storage costs and captures irrelevant data. This paper proposes a declarative framework for intent-driven, on-device data collection that enables selective collection of multimodal sensor data based on high-level user requests. The framework combines natural language interaction with a formally specified domain-specific language (DSL). Large language models translate user-defined requirements into verifiable and composable DSL programs that define conditional triggers across heterogeneous sensors, including cameras, LiDAR, and system telemetry. Empirical evaluation on vehicular and robotic perception tasks shows that the DSL-based approach achieves higher generation consistency and lower execution latency than unconstrained code generation while maintaining comparable detection performance. The structured abstraction supports modular trigger composition and concurrent deployment on resource-constrained edge platforms. This approach replaces passive logging with a verifiable, intent-driven mechanism for multimodal data collection in real-time systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13046 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection Reis, Philipp Rigoll, Philipp Zehetner, Martin Henle, Jacqueline Otten, Stefan Sax, Eric Databases Computation and Language Information Retrieval Machine Learning Programming Languages Data-driven systems depend on task-relevant data, yet data collection pipelines remain passive and indiscriminate. Continuous logging of multimodal sensor streams incurs high storage costs and captures irrelevant data. This paper proposes a declarative framework for intent-driven, on-device data collection that enables selective collection of multimodal sensor data based on high-level user requests. The framework combines natural language interaction with a formally specified domain-specific language (DSL). Large language models translate user-defined requirements into verifiable and composable DSL programs that define conditional triggers across heterogeneous sensors, including cameras, LiDAR, and system telemetry. Empirical evaluation on vehicular and robotic perception tasks shows that the DSL-based approach achieves higher generation consistency and lower execution latency than unconstrained code generation while maintaining comparable detection performance. The structured abstraction supports modular trigger composition and concurrent deployment on resource-constrained edge platforms. This approach replaces passive logging with a verifiable, intent-driven mechanism for multimodal data collection in real-time systems. |
| title | A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection |
| topic | Databases Computation and Language Information Retrieval Machine Learning Programming Languages |
| url | https://arxiv.org/abs/2604.13046 |