# PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts

arXiv: https://arxiv.org/abs/2503.06706 · HTML: https://mlsanity.com/paper/2503.06706/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting](https://mlsanity.com/paper/2305.09067/) (2023)
- [ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation](https://mlsanity.com/paper/2307.15290/) (2023)
- [Exploring Zero and Few-shot Techniques for Intent Classification](https://mlsanity.com/paper/2305.07157/) (2023)
- [CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks](https://mlsanity.com/paper/2310.14623/) (2023)
- [Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs](https://mlsanity.com/paper/2402.11218/) (2024)
- [TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities](https://mlsanity.com/paper/2407.21693/) (2024)
- [SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation](https://mlsanity.com/paper/2307.04907/) (2023)

## Built on by (most cited first, 3 of 3)

- [FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning](https://mlsanity.com/paper/2602.14035/) (2026)
- [JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees](https://mlsanity.com/paper/2603.22978/) (2026)
- [DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue](https://mlsanity.com/paper/2606.17904/) (2026)

## Abstract (arXiv)

Process-driven dialogue systems, which operate under strict predefined process constraints, are essential in customer service and equipment maintenance scenarios. Although Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, they still struggle to solve these strictly constrained dialogue tasks. To address this challenge, we construct Process Flow Dialogue (PFDial) dataset, which contains 12,705 high-quality Chinese dialogue instructions derived from 440 flowcharts containing 5,055 process nodes. Based on PlantUML specification, each UML flowchart is converted into atomic dialogue units i.e., structured five-tuples. Experimental results demonstrate that a 7B model trained with merely 800 samples, and a 0.5B model trained on total data both can surpass 90% accuracy. Additionally, the 8B model can surpass GPT-4o up to 43.88% with an average of 11.00%. We further evaluate models' performance on challenging backward transitions in process flows and conduct an in-depth analysis of various dataset formats to reveal their impact on model performance in handling decision and sequential branches. The data is released in https://github.com/KongLongGeFDU/PFDial.