CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

• URL: http://arxiv.org/abs/2506.02264v2
• Date: Tue, 21 Oct 2025 01:44:36 GMT
• Title: CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
• Authors: Radin Shayanfar, Chu Fei Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu,
• Abstract summary: We introduce a novel framework, CoDial, which converts a TOD task schema to programmatic guardrailing code, such as NVIDIA's Colang.<n>CoDial achieves state-of-the-art (SOTA) performance on the widely used STAR dataset and is on par with SOTA on the MultiWOZ dataset.
• Score: 14.098358830189959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often struggle to transfer effectively to unseen tasks. While recent schema-based TOD frameworks improve generalization by decoupling task logic from language understanding, their reliance on neural or generative models often obscures how task schemas influence behaviour and hence impair interpretability. In this work, we introduce a novel framework, CoDial (Code for Dialogue), which converts a TOD task schema, represented as a novel structured heterogeneous graph, to programmatic LLM guardrailing code, such as NVIDIA's Colang, enabling interpretable and efficient alignment of dialogue policies during inference. We introduce two paradigms, $\text{CoDial}_{\text{free}}$ and $\text{CoDial}_{\text{structured}}$ for generating LLM guardrails, and propose a feedback mechanism that integrates human feedback to iteratively improve the generated code. Empirically, CoDial achieves state-of-the-art (SOTA) performance on the widely used STAR dataset and is on par with SOTA on the MultiWOZ dataset, while also providing interpretability. We additionally demonstrate CoDial's iterative improvement via manual and LLM-aided feedback, making it a practical tool for expert-guided alignment of LLMs in high-stakes domains.

Related papers

• Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior [10.041741229516141]
  Large Language Models (LLMs) allow developers to govern model behavior by editing prompt instructions.<n>We operationalize this paradigm in an interactive system designed to address the challenge of encoding subtle, domain-specific policies into prompt instructions.
  arXiv  Detail & Related papers  (2025-10-14T17:07:37Z)
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models [99.85131798240808]
  We introduce a novel generative framework called textitGuided Topology Diffusion (GTD)<n>Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process.<n>At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards.<n>Experiments show that GTD can generate highly task-adaptive, sparse, and efficient communication topologies.
  arXiv  Detail & Related papers  (2025-10-09T05:28:28Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs [3.9190413787169414]
  Current large language models (LLMs) excel at general NLP tasks but often lack domain specific precision in professional settings.<n>We introduce ProKG Dial, a framework for constructing knowledge intensive multi turn dialogue using domain specific knowledge graphs (KGs)<n>We validate ProKG Dial on a medical knowledge graph by evaluating the generated dialogues in terms of diversity, semantic coherence, and entity coverage.
  arXiv  Detail & Related papers  (2025-08-03T17:52:42Z)
• Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work [0.456877715768796]
  Knowledge Protocol Engineering (KPE) is a new paradigm focused on systematically translating human expert knowledge into a machine-executable Knowledge Protocol.<n>We argue that a well-engineered Knowledge Protocol allows a generalist LLM to function as a specialist, capable of decomposing abstract queries and executing complex, multi-step tasks.
  arXiv  Detail & Related papers  (2025-07-03T16:21:14Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting [24.67373225584835]
  Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training.<n>These models struggle with a fundamental dilemma: direct adaptation approaches that inject domain-specific knowledge often trigger catastrophic forgetting of foundational visual-linguistic abilities.<n>We introduce Structured Dialogue Fine-Tuning (SDFT), an effective approach that effectively injects domain-specific knowledge while minimizing catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-04-27T18:04:02Z)
• Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation [12.077740860502878]
  Embodied long-horizon manipulation requires robotic systems to process multimodal inputs-such as vision and natural language-and translate them into executable actions.<n>Recent methods have explored using large language models (LLMs) as high-level planners that decompose tasks into subtasks using natural language and guide pretrained low-level controllers.<n>Our framework achieves state-of-the-art performance on 30+ diverse seen and unseen long-horizon tasks across LoHoRavens, CALVIN, Franka Kitchen, and cluttered real-world settings.
  arXiv  Detail & Related papers  (2025-03-27T20:32:58Z)
• New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration [49.180693704510006]
  Referring Expression (REC) is a cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding.<n>It serves as an essential testing ground for Multimodal Large Language Models (MLLMs)
  arXiv  Detail & Related papers  (2025-02-27T13:58:44Z)
• Conversation Routines: A Prompt Engineering Framework for Task-Oriented Dialog Systems [0.21756081703275998]
  This study introduces Conversation Routines (CR), a structured prompt engineering framework for developing task-oriented dialog systems using Large Language Models (LLMs)<n>The proposed CR framework enables the development of Conversation Agentic Systems (CAS) through natural language specifications.<n>We demonstrate the framework's effectiveness through two proof-of-concept implementations: a Train Booking System and an Interactive Ticket Copilot.
  arXiv  Detail & Related papers  (2025-01-20T17:19:02Z)
• Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion [20.973071287301067]
  Large Language Models (LLMs) present massive inherent knowledge and superior semantic comprehension capability.<n> Empirical evidence suggests that LLMs consistently perform worse than conventional knowledge graph completion approaches.<n>We propose a novel instruction-tuning-based method, namely FtG, to address these challenges.
  arXiv  Detail & Related papers  (2024-12-12T09:22:04Z)
• Interactive and Expressive Code-Augmented Planning with Large Language Models [62.799579304821826]
  Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
  arXiv  Detail & Related papers  (2024-11-21T04:23:17Z)
• Towards More Unified In-context Visual Understanding [74.55332581979292]
  We present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them.
  arXiv  Detail & Related papers  (2023-12-05T06:02:21Z)
• Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems [53.38517204698343]
  We propose a novel paradigm that uses a textual interface to align external knowledge and eliminate redundant processes. We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database.
  arXiv  Detail & Related papers  (2023-05-23T05:48:21Z)
• Knowledge-grounded Dialog State Tracking [12.585986197627477]
  We propose to perform dialog state tracking grounded on knowledge encoded externally. We query relevant knowledge of various forms based on the dialog context. We demonstrate superior performance of our proposed method over strong baselines.
  arXiv  Detail & Related papers  (2022-10-13T01:34:08Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• Dialogue Meaning Representation for Task-Oriented Dialogue Systems [51.91615150842267]
  We propose Dialogue Meaning Representation (DMR), a flexible and easily extendable representation for task-oriented dialogue. Our representation contains a set of nodes and edges with inheritance hierarchy to represent rich semantics for compositional semantics and task-specific concepts. We propose two evaluation tasks to evaluate different machine learning based dialogue models, and further propose a novel coreference resolution model GNNCoref for the graph-based coreference resolution task.
  arXiv  Detail & Related papers  (2022-04-23T04:17:55Z)
• Continual Learning in Task-Oriented Dialogue Systems [49.35627673523519]
  Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. We propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings.
  arXiv  Detail & Related papers  (2020-12-31T08:44:25Z)
• 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)
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [49.39150449455407]
  HDNO is an option framework for designing latent dialogue acts to avoid designing specific dialogue act representations. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA.
  arXiv  Detail & Related papers  (2020-06-11T20:55:28Z)

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.