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

Yiyou Sun, Junjie Hu, Wei Cheng, Haifeng Chen
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47033-47055, 2024.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-sun24e, title = {{DFA}-{RAG}: Conversational Semantic Router for Large Language Model with Definite Finite Automaton}, author = {Sun, Yiyou and Hu, Junjie and Cheng, Wei and Chen, Haifeng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {47033--47055}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/sun24e/sun24e.pdf}, url = {https://proceedings.mlr.press/v235/sun24e.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton %A Yiyou Sun %A Junjie Hu %A Wei Cheng %A Haifeng Chen %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-sun24e %I PMLR %P 47033--47055 %U https://proceedings.mlr.press/v235/sun24e.html %V 235 %X 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.
APA
Sun, Y., Hu, J., Cheng, W. & Chen, H.. (2024). DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:47033-47055 Available from https://proceedings.mlr.press/v235/sun24e.html.

Related Material