Salvato in:
Dettagli Bibliografici
Autori principali: Birkmose, Rune, Reece, Nathan Mørkeberg, Norvin, Esben Hofstedt, Bjerva, Johannes, Zhang, Mike
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.12923
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908276538474496
author Birkmose, Rune
Reece, Nathan Mørkeberg
Norvin, Esben Hofstedt
Bjerva, Johannes
Zhang, Mike
author_facet Birkmose, Rune
Reece, Nathan Mørkeberg
Norvin, Esben Hofstedt
Bjerva, Johannes
Zhang, Mike
contents This paper investigates whether Large Language Models (LLMs), fine-tuned on synthetic but domain-representative data, can perform the twofold task of (i) slot and intent detection and (ii) natural language response generation for a smart home assistant, while running solely on resource-limited, CPU-only edge hardware. We fine-tune LLMs to produce both JSON action calls and text responses. Our experiments show that 16-bit and 8-bit quantized variants preserve high accuracy on slot and intent detection and maintain strong semantic coherence in generated text, while the 4-bit model, while retaining generative fluency, suffers a noticeable drop in device-service classification accuracy. Further evaluations on noisy human (non-synthetic) prompts and out-of-domain intents confirm the models' generalization ability, obtaining around 80--86\% accuracy. While the average inference time is 5--6 seconds per query -- acceptable for one-shot commands but suboptimal for multi-turn dialogue -- our results affirm that an on-device LLM can effectively unify command interpretation and flexible response generation for home automation without relying on specialized hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation
Birkmose, Rune
Reece, Nathan Mørkeberg
Norvin, Esben Hofstedt
Bjerva, Johannes
Zhang, Mike
Computation and Language
This paper investigates whether Large Language Models (LLMs), fine-tuned on synthetic but domain-representative data, can perform the twofold task of (i) slot and intent detection and (ii) natural language response generation for a smart home assistant, while running solely on resource-limited, CPU-only edge hardware. We fine-tune LLMs to produce both JSON action calls and text responses. Our experiments show that 16-bit and 8-bit quantized variants preserve high accuracy on slot and intent detection and maintain strong semantic coherence in generated text, while the 4-bit model, while retaining generative fluency, suffers a noticeable drop in device-service classification accuracy. Further evaluations on noisy human (non-synthetic) prompts and out-of-domain intents confirm the models' generalization ability, obtaining around 80--86\% accuracy. While the average inference time is 5--6 seconds per query -- acceptable for one-shot commands but suboptimal for multi-turn dialogue -- our results affirm that an on-device LLM can effectively unify command interpretation and flexible response generation for home automation without relying on specialized hardware.
title On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation
topic Computation and Language
url https://arxiv.org/abs/2502.12923