FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning

Read full text
Authors: Jinzi Zou, Bolin Wang, Shuo Zhang, Nuo Xu, Junzhou Zhao
Cited by: 0

Abstract

Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decisionmaking or operational procedures by following a domain-specific flowchart to achieve a task goal.In this work, we formalize flowchart reasoning in FOD as grounding user input to flowchart nodes at each dialogue turn while ensuring node transition is consistent with the correct flowchart path.Despite recent advances of LLMs in task-oriented dialogue systems, adapting them to FOD still faces two limitations: (1) LLMs lack an explicit mechanism to represent and reason over flowchart topology, and (2) they are prone to hallucinations, leading to unfaithful flowchart reasoning.To address these limitations, we propose FloCA, a zero-shot flowchart-oriented conversational agent.FloCA uses an LLM for intent understanding and response generation, while delegating flowchart reasoning to an external tool that performs topology-constrained graph execution, ensuring faithful and logically consistent node transitions across dialogue turns.We further introduce an evaluation framework with an LLM-based user simulator and five new metrics covering reasoning accuracy and interaction efficiency.Extensive experiments on FLODIAL and PFDial datasets highlight the bottlenecks of existing LLM/VLMbased methods and demonstrate the superiority of FloCA.The code and dataset are publicly available at https://github.com/ Jinzi-Zou/FloCA-flowchart-reasoning.A fuse wire has blown in my car.How can I fix it?Please check whether there is a short circuit.How do I check if my car has a short circuit?Using a multimeter and set it to resistance measurement.There is no short circuit in the car.Use a new fuse wire with the same or slightly lower rating YesShort after blown wire?Replace with new fuse wire rated same or lower.

Fields of Study & Subjects

Speech and dialogue systems AI in Service Interactions Intelligent Tutoring Systems and Adaptive Learning

Publication details

Journal / source
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Pages
96–119
Publication date
1 January 2026
Language
EN