Retrieval-Augmented Generation is as a paradigm that integrates the parametric knowledge of a Large Language Model with external non-parametric information through a retrieval component. While RAGs have shown strong performances on several tasks, their answers may still be prone to errors as of the approximate nature of the retrieval process they utilize. In this paper, we argue that the output of a dense retriever can be interpreted as a set of noisy samples that could be retrieved via a query that it is implicitly executed over the data. A symbolic representation of a query that leads to the same results as the set obtained via the dense retriever can then be reconstructed from the samples and used to compute the final augmented result. We instantiate this idea in a concrete retrieval architecture, which we call Symbolic-Assisted Dense Retriever, and present a preliminary use case scenario and experimental evaluation.
Enhancing Retrieval-Augmented Generators with Symbolic Query Definitions / Bianchini, F., Calamo, M., Console, M., Mecella, M., Papi, L.. - 4229:(2026), pp. 187-200. (Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs Lisbon; Portugal ).
Enhancing Retrieval-Augmented Generators with Symbolic Query Definitions
Bianchini F.;Calamo M.;Console M.;Mecella M.;Papi L.
2026
Abstract
Retrieval-Augmented Generation is as a paradigm that integrates the parametric knowledge of a Large Language Model with external non-parametric information through a retrieval component. While RAGs have shown strong performances on several tasks, their answers may still be prone to errors as of the approximate nature of the retrieval process they utilize. In this paper, we argue that the output of a dense retriever can be interpreted as a set of noisy samples that could be retrieved via a query that it is implicitly executed over the data. A symbolic representation of a query that leads to the same results as the set obtained via the dense retriever can then be reconstructed from the samples and used to compute the final augmented result. We instantiate this idea in a concrete retrieval architecture, which we call Symbolic-Assisted Dense Retriever, and present a preliminary use case scenario and experimental evaluation.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


