@inproceedings{hua-etal-2025-picd,
title = "{PICD}-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding",
author = "Hua, Wenbin and
Fan, Rui and
He, Tingting and
Dong, Ming",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.265/",
pages = "4942--4956",
ISBN = "979-8-89176-335-7",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hua-etal-2025-picd">
<titleInfo>
<title>PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenbin</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">hua-etal-2025-picd</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.265/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>4942</start>
<end>4956</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding
%A Hua, Wenbin
%A Fan, Rui
%A He, Tingting
%A Dong, Ming
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F hua-etal-2025-picd
%X 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.
%U https://aclanthology.org/2025.findings-emnlp.265/
%P 4942-4956
Markdown (Informal)
[PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understanding](https://aclanthology.org/2025.findings-emnlp.265/) (Hua et al., Findings 2025)
ACL