PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding

Wenbin Hua, Rui Fan, Tingting He, Ming Dong


Abstract
Few-shot multi-intent spoken language understanding (SLU) aims to identify users’ multiple intents and key slots using a tiny amount of annotated data. Recent advances in large language models (LLMs) have utilized instruction learning frameworks to model intent-slot interdependencies, typically requiring abundant data for effective training. However, in few-shot scenarios, these frameworks face challenges such as mismatches between the number of generated slots and input lengths, relational confusion in multi-intent scenarios and neglect of task-specific variations in intent counts across utterances. To overcome the challenges, we propose PICD-Instruct, a novel generative framework based on Basic Instructions (BI), Pairwise Interaction Instructions (PII) and Contrastive Distinct Instructions (CDI). Specifically, BI directs LLMs to generate entities along with associated words, thereby mitigating mismatches in quantitative correspondences. PII explicitly captures dual-task interdependencies by guiding LLMs to pair each intent with its related entities. CDI enhances understanding of utterances by guiding LLMs to determine whether two utterances share the same intent count. Experimental results on public datasets indicate that PICD-Instruct achieves state-of-the-art performance.
Anthology ID:
2025.findings-emnlp.265
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4942–4956
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.265/
DOI:
Bibkey:
Cite (ACL):
Wenbin Hua, Rui Fan, Tingting He, and Ming Dong. 2025. PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 4942–4956, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding (Hua et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.265.pdf
Checklist:
 2025.findings-emnlp.265.checklist.pdf