@article{finch-etal-2026-generative,
title = "Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions",
author = "Finch, James D. and
Josyula, Yasasvi and
Choi, Jinho D.",
journal = "Transactions of the Association for Computational Linguistics",
volume = "14",
year = "2026",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2026.tacl-1.5/",
doi = "10.1162/tacl.a.66",
pages = "81--99",
abstract = "In task-oriented dialogue (TOD) systems, Slot Schema Induction (SSI) is essential for automatically identifying key information slots from dialogue data without manual intervention. This paper presents a novel state-of-the-art (SotA) approach that formulates SSI as a text generation task, where a language model incrementally constructs and refines a slot schema over a stream of dialogue data. To develop this approach, we present a fully automatic LLM-based TOD simulation method that creates data with high-quality state labels for novel task domains. Furthermore, we identify issues in SSI evaluation due to data leakage and poor metric alignment with human judgment. We resolve these by creating new evaluation data using our simulation method with human guidance and correction, as well as designing improved evaluation metrics. These contributions establish a foundation for future SSI research and advance the SotA in dialogue understanding and system development."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="finch-etal-2026-generative">
<titleInfo>
<title>Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasasvi</namePart>
<namePart type="family">Josyula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>In task-oriented dialogue (TOD) systems, Slot Schema Induction (SSI) is essential for automatically identifying key information slots from dialogue data without manual intervention. This paper presents a novel state-of-the-art (SotA) approach that formulates SSI as a text generation task, where a language model incrementally constructs and refines a slot schema over a stream of dialogue data. To develop this approach, we present a fully automatic LLM-based TOD simulation method that creates data with high-quality state labels for novel task domains. Furthermore, we identify issues in SSI evaluation due to data leakage and poor metric alignment with human judgment. We resolve these by creating new evaluation data using our simulation method with human guidance and correction, as well as designing improved evaluation metrics. These contributions establish a foundation for future SSI research and advance the SotA in dialogue understanding and system development.</abstract>
<identifier type="citekey">finch-etal-2026-generative</identifier>
<identifier type="doi">10.1162/tacl.a.66</identifier>
<location>
<url>https://aclanthology.org/2026.tacl-1.5/</url>
</location>
<part>
<date>2026</date>
<detail type="volume"><number>14</number></detail>
<extent unit="page">
<start>81</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions
%A Finch, James D.
%A Josyula, Yasasvi
%A Choi, Jinho D.
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F finch-etal-2026-generative
%X In task-oriented dialogue (TOD) systems, Slot Schema Induction (SSI) is essential for automatically identifying key information slots from dialogue data without manual intervention. This paper presents a novel state-of-the-art (SotA) approach that formulates SSI as a text generation task, where a language model incrementally constructs and refines a slot schema over a stream of dialogue data. To develop this approach, we present a fully automatic LLM-based TOD simulation method that creates data with high-quality state labels for novel task domains. Furthermore, we identify issues in SSI evaluation due to data leakage and poor metric alignment with human judgment. We resolve these by creating new evaluation data using our simulation method with human guidance and correction, as well as designing improved evaluation metrics. These contributions establish a foundation for future SSI research and advance the SotA in dialogue understanding and system development.
%R 10.1162/tacl.a.66
%U https://aclanthology.org/2026.tacl-1.5/
%U https://doi.org/10.1162/tacl.a.66
%P 81-99
Markdown (Informal)
[Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions](https://aclanthology.org/2026.tacl-1.5/) (Finch et al., TACL 2026)
ACL