Imagen de Portada

On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Birkmose, Rune, Reece, Nathan Mørkeberg, Norvin, Esben Hofstedt, Bjerva, Johannes, Zhang, Mike
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Responsible Development of Automated Student Feedback with Generative AI
por: Lindsay, Euan D, et al.
Publicado: (2023)

Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality
por: Zhang, Mike, et al.
Publicado: (2025)

Patterns of Persistence and Diffusibility across the World's Languages
por: Chen, Yiyi, et al.
Publicado: (2024)

Linguistically Grounded Analysis of Language Models using Shapley Head Values
por: Fekete, Marcell, et al.
Publicado: (2024)

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
por: Luo, Xiaoyu, et al.
Publicado: (2025)

Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
por: Luo, Xiaoyu, et al.
Publicado: (2026)

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
por: Luo, Xiaoyu, et al.
Publicado: (2026)

Multilingual Gradient Word-Order Typology from Universal Dependencies
por: Baylor, Emi, et al.
Publicado: (2024)

When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs
por: Fekete, Marcell, et al.
Publicado: (2026)

SEFL: A Framework for Generating Synthetic Educational Assignment Feedback with LLM Agents
por: Zhang, Mike, et al.
Publicado: (2025)

Intent Detection in the Age of LLMs
por: Arora, Gaurav, et al.
Publicado: (2024)

Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls
por: Aavang, Rasmus T., et al.
Publicado: (2026)

Leveraging Large Language Models for Actionable Course Evaluation Student Feedback to Lecturers
por: Zhang, Mike, et al.
Publicado: (2024)

Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
por: Bolshinsky, Inbal, et al.
Publicado: (2025)

ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
por: Chen, Yiyi, et al.
Publicado: (2025)

MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
por: Lavrinovics, Ernests, et al.
Publicado: (2025)

Text Embedding Inversion Security for Multilingual Language Models
por: Chen, Yiyi, et al.
Publicado: (2024)

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices
por: Li, Silin, et al.
Publicado: (2025)

What is "Typological Diversity" in NLP?
por: Ploeger, Esther, et al.
Publicado: (2024)

Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
por: Chen, Yiyi, et al.
Publicado: (2024)

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
por: Wang, Pei, et al.
Publicado: (2024)

Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification
por: Tatariya, Kushal, et al.
Publicado: (2024)

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
por: Liu, Xiao, et al.
Publicado: (2024)

Generate then Refine: Data Augmentation for Zero-shot Intent Detection
por: Lin, I-Fan, et al.
Publicado: (2024)

Evaluating LLMs at Detecting Errors in LLM Responses
por: Kamoi, Ryo, et al.
Publicado: (2024)

LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation
por: Fu, Junchen, et al.
Publicado: (2025)

CALYPSO: LLMs as Dungeon Masters' Assistants
por: Zhu, Andrew, et al.
Publicado: (2023)

Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
por: Castillo-López, Galo, et al.
Publicado: (2025)

DROID: Dual Representation for Out-of-Scope Intent Detection
por: Rashwan, Wael, et al.
Publicado: (2025)

Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling
por: Feng, Zihao, et al.
Publicado: (2025)

A Generative Model for Joint Multiple Intent Detection and Slot Filling
por: Li, Liz, et al.
Publicado: (2026)

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective
por: Lavrinovics, Ernests, et al.
Publicado: (2024)

Mitigating Jailbreaks with Intent-Aware LLMs
por: Yeo, Wei Jie, et al.
Publicado: (2025)

User-Assistant Bias in LLMs
por: Pan, Xu, et al.
Publicado: (2025)

Replicating ReLM Results: Validating Large Language Models with ReLM
por: Adamson, Reece, et al.
Publicado: (2025)

NaturalTurn: A Method to Segment Speech into Psychologically Meaningful Conversational Turns
por: Cooney, Gus, et al.
Publicado: (2024)

LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
por: Yu, Wenrui, et al.
Publicado: (2025)

Known Intents, New Combinations: Clause-Factorized Decoding for Compositional Multi-Intent Detection
por: Nandy, Abhilash
Publicado: (2026)

Towards a World-English Language Model for On-Device Virtual Assistants
por: Jalota, Rricha, et al.
Publicado: (2024)

Multi Agent based Medical Assistant for Edge Devices
por: Gawade, Sakharam, et al.
Publicado: (2025)