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

• URL: http://arxiv.org/abs/2603.09691v1
• Date: Tue, 10 Mar 2026 13:59:02 GMT
• Title: ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling
• Abstract summary: We propose ESAinsTOD, a unified End-to-end- instruction-tuning framework for task-oriented dialog modeling.<n>We go beyond simply fine-tuning Large Language Models (LLMs), enabling flexible adaptation to various dialogue task flows and schemas.<n>We show that ESAinsTOD outperforms state-of-the-art models by a significant margin on end-to-end task-oriented dialog modeling benchmarks.
• Score: 44.73279314406119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs [2.1793134762413433]
  AI agents need to plan to achieve complex goals that involve orchestrating perception, sub-goal decomposition, and execution.<n>Existing research on foundational models' understanding of temporal execution is limited to automatically derived annotations, approximations of the TEO as a linear chain, or text-only inputs.<n>We introduce MATEO, a benchmark designed to assess and improve the temporal reasoning abilities of Large Vision Language Models (LVLMs) required for real-world planning.
  arXiv  Detail & Related papers  (2026-02-16T09:41:50Z)
• AR-MOT: Autoregressive Multi-object Tracking [56.09738000988466]
  We propose a novel autoregressive paradigm that formulates MOT as a sequence generation task within a large language model (LLM) framework.<n>This design enables the model to output structured results through flexible sequence construction, without requiring any task-specific heads.<n>To enhance region-level visual perception, we introduce an Object Tokenizer based on a pretrained detector.
  arXiv  Detail & Related papers  (2026-01-05T09:17:28Z)
• Evaluating and Enhancing Out-of-Domain Generalization of Task-Oriented Dialog Systems for Task Completion without Turn-level Dialog Annotations [2.453775887722866]
  This work explores whether large language models (LLMs) can be fine-tuned solely on natural language dialogs to perform ToD tasks, without requiring such annotations.<n>We find that models fine-tuned without turn-level annotations generate coherent and contextually appropriate responses.<n>We propose ZeroToD, a framework that incorporates a schema augmentation mechanism to enhance API call accuracy and overall task completion rates.
  arXiv  Detail & Related papers  (2025-02-18T22:10:51Z)
• Matchmaker: Self-Improving Large Language Model Programs for Schema Matching [60.23571456538149]
  We propose a compositional language model program for schema matching, comprised of candidate generation, refinement and confidence scoring. Matchmaker self-improves in a zero-shot manner without the need for labeled demonstrations. Empirically, we demonstrate on real-world medical schema matching benchmarks that Matchmaker outperforms previous ML-based approaches.
  arXiv  Detail & Related papers  (2024-10-31T16:34:03Z)
• OSM: Leveraging Model Checking for Observing Dynamic 1 behaviors in Aspect-Oriented Applications [0.0]
  observe-based statistical model-checking (OSM) framework devised to craft executable formal models directly from foundational system code. This ensures the unyielding performance of electronic health record systems amidst shifting preconditions.
  arXiv  Detail & Related papers  (2024-03-03T00:03:34Z)
• InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models [9.611864685207056]
  We propose a novel approach, InstructERC, to reformulate the emotion recognition task from a discriminative framework to a generative framework based on Large Language Models (LLMs) InstructERC makes three significant contributions: (1) it introduces a simple yet effective retrieval template module, which helps the model explicitly integrate multi-granularity dialogue supervision information; (2) we introduce two additional emotion alignment tasks, namely speaker identification and emotion prediction tasks, to implicitly model the dialogue role relationships and future emotional tendencies in conversations; and (3) Pioneeringly, we unify emotion labels across benchmarks through the feeling wheel to fit real application scenarios.
  arXiv  Detail & Related papers  (2023-09-21T09:22:07Z)
• Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema [2.7178968279054936]
  State-of-the-art approaches in task-oriented dialog systems formulate the problem as a conditional sequence generation task. This requires labeled training data for each new domain or task. We introduce a novel Zero-Shot generalizable end-to-end Task-oriented Dialog system, ZS-ToD.
  arXiv  Detail & Related papers  (2023-03-28T18:56:31Z)
• A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking [78.2700757742992]
  Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness. We propose a single multi-task BERT-based model that jointly solves the three DST tasks of intent prediction, requested slot prediction and slot filling.
  arXiv  Detail & Related papers  (2022-07-02T13:27:59Z)
• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems [56.302581679816775]
  This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD. Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
  arXiv  Detail & Related papers  (2021-09-10T03:23:06Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.