ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling

2026-03-10

AI Summary

This work proposes ESAinsTOD, a unified framework for end-to-end task-oriented dialogue systems that addresses the limited generalization of existing approaches, which are typically tailored to specific datasets. By integrating instruction tuning with a structured alignment mechanism, ESAinsTOD equips large language models with both instruction-aware and schema-aware capabilities, enabling conversation-level modeling across diverse task flows. The method combines full-parameter fine-tuning with joint instruction and schema alignment, significantly enhancing model generalization in cross-dataset, low-resource, and zero-shot settings while improving robustness against noise and cascading errors. Experimental results demonstrate that ESAinsTOD consistently outperforms state-of-the-art methods on benchmark datasets including CamRest676, In-Car, and MultiWOZ.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Existing end-to-end modeling methods for modular task-oriented dialog systems are typically tailored to specific datasets, making it challenging to adapt to new dialog scenarios. In this work, we propose ESAinsTOD, a unified End-to-end Schema-Aware Instruction-tuning framework for general Task-Oriented Dialog modeling. This framework introduces a structured methodology to go beyond simply fine-tuning Large Language Models (LLMs), enabling flexible adaptation to various dialogue task flows and schemas. Specifically, we leverage full-parameter fine-tuning of LLMs and introduce two alignment mechanisms to make the resulting system both instruction-aware and schema-aware: (i) instruction alignment, which ensures that the system faithfully follows task instructions to complete various task flows from heterogeneous TOD datasets; and (ii) schema alignment, which encourages the system to make predictions adhering to the specified schema. In addition, we employ session-level end-to-end modeling, which allows the system to access the results of previously executed task flows within the dialogue history, to bridge the gap between the instruction-tuning paradigm and the real-world application of TOD systems. Empirical results show that while a fine-tuned LLM serves as a strong baseline, our structured approach provides significant additional benefits. In particular, our findings indicate that: (i) ESAinsTOD outperforms state-of-the-art models by a significant margin on end-to-end task-oriented dialog modeling benchmarks: CamRest676, In-Car and MultiWOZ; (ii) more importantly, it exhibits superior generalization capabilities across various low-resource settings, with the proposed alignment mechanisms significantly enhancing zero-shot performance; and (iii) our instruction-tuning paradigm substantially improves the model's robustness against data noise and cascading errors.

Problem

• Task-Oriented Dialog
• End-to-End Modeling
• Schema Adaptation
• Generalization
• Instruction Tuning

Innovation

• schema-aware
• instruction-tuning
• end-to-end modeling
• task-oriented dialog
• alignment mechanisms