@inproceedings{gao-choi-2026-building,
title = "Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data",
author = "Gao, Henry and
Choi, Jinho D.",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.54/",
pages = "773--785",
abstract = "Task-oriented dialogue (TOD) systems conventionally rely on supervised fine-tuning over large datasets, an approach that is both resource-intensive and difficult to generalize across domains. We investigate whether large language models (LLMs) can serve as effective TOD agents without any fine-tuning, relying solely on in-context prompting and unstructured conversational logs. To this end, we propose a two-stage framework in which an LLM first induces structured procedural instructions from raw multi-turn dialogues, then leverages these instructions to generate goal-oriented interactions. An iterative refinement loop further improves instruction quality by evaluating intermediate dialogue outputs and propagating feedback to update the instructions. To address limitations inherent in existing evaluation protocols, we introduce an interactive evaluation framework centered on a constrained user simulator with access to ground-truth task goals. This design enables flexible assessment of task success beyond fixed dialogue trajectories, more faithfully reflecting the conditions of real-world deployment. Experiments demonstrate that the proposed approach produces coherent and task-effective dialogues without any annotated data. Using Gemma-3-27b-it as the backbone, our system achieves a dialogue state F1 of 86.3{\%}, outperforming GALAXY (84.3{\%}) and MARS (84.6{\%})."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-choi-2026-building">
<titleInfo>
<title>Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Gao</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>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Task-oriented dialogue (TOD) systems conventionally rely on supervised fine-tuning over large datasets, an approach that is both resource-intensive and difficult to generalize across domains. We investigate whether large language models (LLMs) can serve as effective TOD agents without any fine-tuning, relying solely on in-context prompting and unstructured conversational logs. To this end, we propose a two-stage framework in which an LLM first induces structured procedural instructions from raw multi-turn dialogues, then leverages these instructions to generate goal-oriented interactions. An iterative refinement loop further improves instruction quality by evaluating intermediate dialogue outputs and propagating feedback to update the instructions. To address limitations inherent in existing evaluation protocols, we introduce an interactive evaluation framework centered on a constrained user simulator with access to ground-truth task goals. This design enables flexible assessment of task success beyond fixed dialogue trajectories, more faithfully reflecting the conditions of real-world deployment. Experiments demonstrate that the proposed approach produces coherent and task-effective dialogues without any annotated data. Using Gemma-3-27b-it as the backbone, our system achieves a dialogue state F1 of 86.3%, outperforming GALAXY (84.3%) and MARS (84.6%).</abstract>
<identifier type="citekey">gao-choi-2026-building</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.54/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>773</start>
<end>785</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data
%A Gao, Henry
%A Choi, Jinho D.
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F gao-choi-2026-building
%X Task-oriented dialogue (TOD) systems conventionally rely on supervised fine-tuning over large datasets, an approach that is both resource-intensive and difficult to generalize across domains. We investigate whether large language models (LLMs) can serve as effective TOD agents without any fine-tuning, relying solely on in-context prompting and unstructured conversational logs. To this end, we propose a two-stage framework in which an LLM first induces structured procedural instructions from raw multi-turn dialogues, then leverages these instructions to generate goal-oriented interactions. An iterative refinement loop further improves instruction quality by evaluating intermediate dialogue outputs and propagating feedback to update the instructions. To address limitations inherent in existing evaluation protocols, we introduce an interactive evaluation framework centered on a constrained user simulator with access to ground-truth task goals. This design enables flexible assessment of task success beyond fixed dialogue trajectories, more faithfully reflecting the conditions of real-world deployment. Experiments demonstrate that the proposed approach produces coherent and task-effective dialogues without any annotated data. Using Gemma-3-27b-it as the backbone, our system achieves a dialogue state F1 of 86.3%, outperforming GALAXY (84.3%) and MARS (84.6%).
%U https://aclanthology.org/2026.sigdial-1.54/
%P 773-785
Markdown (Informal)
[Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data](https://aclanthology.org/2026.sigdial-1.54/) (Gao & Choi, SIGDIAL 2026)
ACL