# DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton

arXiv: https://arxiv.org/abs/2402.04411 · HTML: https://mlsanity.com/paper/2402.04411/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [OpenOOD: Benchmarking Generalized Out-of-Distribution Detection](https://mlsanity.com/paper/2210.07242/) (2022)
- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.09301/) (2023)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Retrieval-Augmented Multimodal Language Modeling](https://mlsanity.com/paper/2211.12561/) (2022)
- [ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models](https://mlsanity.com/paper/2302.07257/) (2023)
- [Finding Support Examples for In-Context Learning](https://mlsanity.com/paper/2302.13539/) (2023)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Dream the Impossible: Outlier Imagination with Diffusion Models](https://mlsanity.com/paper/2309.13415/) (2023)
- [RET-LLM: Towards a General Read-Write Memory for Large Language Models](https://mlsanity.com/paper/2305.14322/) (2023)
- [Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2305.18846/) (2023)
- [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://mlsanity.com/paper/2308.11761/) (2023)
- [Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention](https://mlsanity.com/paper/1905.12866/) (2019)
- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2305.02468/) (2023)
- [Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System](https://mlsanity.com/paper/2006.06814/) (2020)
- [Multi-Domain Dialogue Acts and Response Co-Generation](https://mlsanity.com/paper/2004.12363/) (2020)
- [A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2311.03524/) (2023)
- [When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis](https://mlsanity.com/paper/2308.05017/) (2023)
- [Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems](https://mlsanity.com/paper/2302.10342/) (2023)
- [How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?](https://mlsanity.com/paper/2312.14452/) (2023)

## Built on by (most cited first, 5 of 5)

- [Scalable UAV Multi-Hop Networking via Multi-Agent Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2505.08448/) (2025)
- [Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption](https://mlsanity.com/paper/2601.12331/) (2026)
- [Exploring How LLMs Capture and Represent Domain-Specific Knowledge](https://mlsanity.com/paper/2504.16871/) (2025)
- [Evidence-in-the-Loop: Trace-Driven Optimization for Customer-Service LLM Agents](https://mlsanity.com/paper/2607.18039/) (2026)
- [S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling](https://mlsanity.com/paper/2608.14029/) (2026)

## Abstract (arXiv)

This paper introduces the retrieval-augmented large language model with Definite Finite Automaton (DFA-RAG), a novel framework designed to enhance the capabilities of conversational agents using large language models (LLMs). Traditional LLMs face challenges in generating regulated and compliant responses in special scenarios with predetermined response guidelines, like emotional support and customer service. Our framework addresses these challenges by embedding a Definite Finite Automaton (DFA), learned from training dialogues, within the LLM. This structured approach acts as a semantic router which enables the LLM to adhere to a deterministic response pathway. The routing is achieved by the retrieval-augmentation generation (RAG) strategy, which carefully selects dialogue examples aligned with the current conversational context. The advantages of DFA-RAG include an interpretable structure through human-readable DFA, context-aware retrieval for responses in conversations, and plug-and-play compatibility with existing LLMs. Extensive benchmarks validate DFA-RAG's effectiveness, indicating its potential as a valuable contribution to the conversational agent.