Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data

Henry Gao, Jinho D. Choi


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%).
Anthology ID:
2026.sigdial-1.54
Volume:
Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
August
Year:
2026
Address:
Atlanta, Georgia, USA
Editors:
Jinho D. Choi, Yun-Nung Chen, Kotaro Funakoshi, Ali Emami
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
773–785
Language:
URL:
https://aclanthology.org/2026.sigdial-1.54/
DOI:
Bibkey:
Cite (ACL):
Henry Gao and Jinho D. Choi. 2026. Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 773–785, Atlanta, Georgia, USA. Association for Computational Linguistics.
Cite (Informal):
Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data (Gao & Choi, SIGDIAL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.sigdial-1.54.pdf