ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pozzi, Riccardo, Palmonari, Matteo, Coletta, Andrea, Bellomarini, Luigi, Lehmann, Jens, Vahdati, Sahar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912718181629952
author Pozzi, Riccardo
Palmonari, Matteo
Coletta, Andrea
Bellomarini, Luigi
Lehmann, Jens
Vahdati, Sahar
author_facet Pozzi, Riccardo
Palmonari, Matteo
Coletta, Andrea
Bellomarini, Luigi
Lehmann, Jens
Vahdati, Sahar
contents Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as Retrieval-Augmented Generation (RAG) and tool use, aim to address these issues by incorporating external knowledge. Yet, they rely on additional models or services, resulting in complex pipelines, potential error propagation, and often requiring the model to process a large number of tokens. In this paper, we present a scalable method that enables LLMs to access external knowledge without depending on retrievers or auxiliary models. Our approach uses constrained generation with a pre-built prefix-tree index. Triples from a Knowledge Graph are verbalized in textual facts, tokenized, and indexed in a prefix tree for efficient access. During inference, to acquire external knowledge, the LLM generates facts with constrained generation which allows only sequences of tokens that form an existing fact. We evaluate our proposal on Question Answering and show that it scales to large knowledge bases (800 million facts), adapts to domain-specific data, and achieves effective results. These gains come with minimal generation-time overhead. ReFactX code is available at https://github.com/rpo19/ReFactX.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
Pozzi, Riccardo
Palmonari, Matteo
Coletta, Andrea
Bellomarini, Luigi
Lehmann, Jens
Vahdati, Sahar
Computation and Language
Artificial Intelligence
I.2.7
Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as Retrieval-Augmented Generation (RAG) and tool use, aim to address these issues by incorporating external knowledge. Yet, they rely on additional models or services, resulting in complex pipelines, potential error propagation, and often requiring the model to process a large number of tokens. In this paper, we present a scalable method that enables LLMs to access external knowledge without depending on retrievers or auxiliary models. Our approach uses constrained generation with a pre-built prefix-tree index. Triples from a Knowledge Graph are verbalized in textual facts, tokenized, and indexed in a prefix tree for efficient access. During inference, to acquire external knowledge, the LLM generates facts with constrained generation which allows only sequences of tokens that form an existing fact. We evaluate our proposal on Question Answering and show that it scales to large knowledge bases (800 million facts), adapts to domain-specific data, and achieves effective results. These gains come with minimal generation-time overhead. ReFactX code is available at https://github.com/rpo19/ReFactX.
title ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2508.16983